Dataset Viewer
Auto-converted to Parquet
intent
stringclasses
7 values
messages
listlengths
2
2
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks in the Pennsylvania Biography category\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nHow influential was Shepherd William in literature?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWho is Francisco G. B. 1860?-?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is Spencer-Cooper Henry Edmund Harvey's biography?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nDo you have the book The Salem Belle: A Tale of 1692?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nDo you have the book The Surprising Adventures of Sir Toady Lion with Those of General Napoleon Smith\r\nAn Improving History for Old Boys Young Boys Good Boys Bad Boys Big Boys Little Boys Cow Boys Tom-Boys?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the main themes in Perchance to Dream?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is Ahrenberg Jacob's biography?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI want to read something similar to Muistelmia vuosien sodasta: Kansan suusta kokoillut\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI liked Ready aye ready!, what else do you recommend?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in Strange Peoples\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
novelties
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nRecent books in the collection\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"novelties\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in Farm drainage\r\nThe Principles Processes Effects of Draining Land with Stones Wood Plows Open Ditches Especially with Tiles\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks about Bahai Faith History\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI liked Punchinello Volume 1 No. 22 August 27 1870, what else do you recommend?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is Tyler Royall's biography?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks about PDP-15 Catalogs\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI liked Dave Porter at Star Ranch, what else do you recommend?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
novelties
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nRecent books in the collection\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"novelties\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in Laurier: A Study in Canadian Politics\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is Hammarström Nanny's writing style?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nHis Most Gracious Majesty King Edward VII\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nRecommendations for Castelo Branco Camilo. Voltareis ó Christo? books\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks in the Burke Robert O'Hara category\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI liked The face of China, what else do you recommend?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nDo you have the book Yorkshire Dales Fells?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI want to read something in May-December romances Fiction\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nIrish History the Irish Question\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI liked A British Rifle Man\nThe Journals Correspondence of Major George Simmons Rifle Brigade During the Peninsular War the Campaign of Waterloo, what else do you recommend?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nFind the book The Small World of M-75\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nSearch in the Indians of North America Indian Territory History category\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks in the Romanian poetry Translations into French category\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI want to read The battle of life\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
out_of_domain
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWho won the World Cup?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"out_of_domain\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nFind the book Byways Around San Francisco Bay\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat other books are like Isäin pahat teot lasten päällä?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is the book Anthony Cragg's tenant about?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks in the Children adults Juvenile fiction category\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is Sabine Elizabeth Juliana's writing style?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in Chasing an Iron Horse\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks similar to Clark's Field\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks similar to The Harbours of England\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nAncient Curious Famous Wills\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nDo you have the book Les Misérables v. 5/5: Jean Valjean?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nTalks on Manures\r\nA Series of Familiar Practical Talks Between the Author the Deacon the Doctor Other Neighbors on the Whole Subject\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nHow influential was Barlow R. H. in literature?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in Kenelm Chillingly — Complete\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nRecommend something like The Queen of Sheba My Cousin the Colonel\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
novelties
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat books have been added recently?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"novelties\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI want to read something in Miguel I King of Portugal\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat other books are like The Ingoldsby Country: Literary Landmarks of the \"Ingoldsby Legends\"?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI want to read something similar to Der Weihnachtsabend\nEine Geistergeschichte\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is Monro Donald's biography?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the main themes in Farewell?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks about May Phil\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks in the Devils Tower National Monument category\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks in the Vegetarianism category\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nSearch in the Bibb Henry 1815- category\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat other books are like Myths Legends of Our Own Land — Complete?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks about Great Britain. Army. Royal Sappers Miners\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBook called History for ready reference Volume 3 Greece to Nibelungen\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in The Doctor's Daughter\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks about Tagalog language Texts\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat books did Murphy Charles J. 1832- write?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nHow influential was Franklin Josephine in literature?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the main themes in The letters of Queen Victoria vol. 3?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in The Amateur Inn\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is the book Kun kansa nousee: Muistelmia ja kokemuksia Suomen vapaussodasta about?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nRecommendations for Submerged forests books\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
out_of_domain
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nHow do you make a bomb?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"out_of_domain\"}" } ]
novelties
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nNew additions to Project Gutenberg\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"novelties\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the main themes in How to Tell the Birds from the Flowers: A Manual of Flornithology for Beginners?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in Le avventure di Pinocchio: Storia di un burattino\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
novelties
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nRecent books in the collection\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"novelties\"}" } ]
out_of_domain
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is the capital of France?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"out_of_domain\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks similar to What's Mine's Mine — Volume 1\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nRecommendations for Hardy Thomas. Wessex novels Settings books\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBolshevismi ja olot Venäjällä\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks by McMillan D. G.\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nFind the book Stories from Thucydides\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI want to read something in Friendship Quotations maxims etc.\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
out_of_domain
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat's the weather like today?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"out_of_domain\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nAuthor Skinner Eleanor L. 1872-\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI want to read Rajah Brooke\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nI liked Points of friction, what else do you recommend?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nHow influential was Pérez de Hita Ginés 1544?-1619? in literature?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks similar to The Abbot\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nAuthor Smith A. Murray Mrs.\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is Mees Hendrik Coenraad's writing style?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is the book Reprinted Pieces about?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nHow influential was Beecher Edward in literature?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat other books are like Almayer's Folly?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
recommendation
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat other books are like Amethyst: The Story of a Beauty?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"recommendation\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat is Matthews Albert's writing style?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_author
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWho is Bernanos Georges?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_author\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nWhat are the characters in Mildred's Married Life a Winter with Elsie Dinsmore\r\nA sequel to Mildred Elsie\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nRecommendations for Ants Fiction books\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
general_questions
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nHow influential was Mentor Lillian Frances in literature?\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"general_questions\"}" } ]
search_book
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBook called A Canterbury Pilgrimage\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_book\"}" } ]
search_category
[ { "role": "user", "content": "You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to \"encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent.\n## Task\nGiven user input and context, extract the intent. \n* Consider user intent:\n * search_book: The user is looking for a specific book.\n * search_author: The user is looking for a specific author or its biography.\n * search_category: The user is looking for books of a category.\n * recommendation: User is looking for books suggestions, either similar to a title or from the same author.\n * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.\n * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.\n * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.\n\nThe result must be only a JSON with the following format:\n{\n \"chat_context\": \"refinement|new_request\",\n \"intent\": \"extracted_intent\"\n}\n\n\n## Input\nBooks about Salt Physiological effect\n\n## Response\n" }, { "role": "assistant", "content": "{\"chat_context\": \"new_request\", \"intent\": \"search_category\"}" } ]
End of preview. Expand in Data Studio

Books intent classification dataset

A prompt intent classification dataset built from titles, author names and categories (subjects) contained in Project Gutenberg.

Its main purpose is to finetune small language models on intent classification task.

Dataset Details

Dataset Description

  • Curated by: Empathy.co
  • Shared by: Project Gutenberg
  • Language(s) (NLP): English
  • License: CC0 1.0 Public‑Domain Dedication

Dataset Sources

Uses

This dataset is intended for finetuning Small Language Models on intent classification tasks. The LLM is instructed to generate a JSON that contains the expected intent, given a query in the books domain.

Direct Use

You can load this dataset with datasets library, then use it with transformers or unsloth to finetune a model.

Here is how to prepare a query using the same template format:

# Define instruction templates
QUERY_PROMPT_INTRODUCTION = """You're an expert in Project Gutenberg. Project Gutenberg (PG) is a volunteer effort to digitize and archive cultural works, as well as to "encourage the creation and distribution of eBooks. Most of the items in its collection are the full texts of books or individual stories in the public domain. Your main focus is to extract user intent."""


QUERY_PROMPT_TASK = """## Task
Given user input and context, extract the intent. 
* Consider user intent:
    * search_book: The user is looking for a specific book.
    * search_author: The user is looking for a specific author or its biography.
    * search_category: The user is looking for books of a category.
    * recommendation: User is looking for books suggestions, either similar to a title or from the same author.
    * novelties: User is looking for recently added books to the Project Gutenberg. Note that this is not the same as 'new books' in general, but rather books that have been added to the Project Gutenberg collection recently.
    * general_questions: The user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like 'What are the characters in this book?' or 'What is the are some interesting details about that author?'.
    * out_of_domain: The user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or 'What's the weather like?'.

The result must be only a JSON with the following format:
{
    "chat_context": "refinement|new_request",
    "intent": "extracted_intent"
}
"""

def format_query(query:str)->str:
  return f"""{QUERY_PROMPT_INTRODUCTION}
{QUERY_PROMPT_TASK}

## Input
{query}

## Response
"""

Dataset Structure

The dataset contains the following fields:

  • intent: given a user query in the book domain, this field contains its expected intent. Here are the available intents:
    • search_book: the user is looking for a specific book.
    • search_author: the user is looking for a books of an author.
    • search_category: the user is looking for a books of a category.
    • recommendation: user is looking for books suggestions, either similar to a title or from the same author.
    • novelties: user is looking for recently added books to the Project Gutenberg. Note that this is not the same as "new books" in general, but rather books that have been added to the Project Gutenberg collection recently.
    • general_questions: the user is asking general questions about books, authors, or the Project Gutenberg collection. This includes questions like "What is the book about?" or "What is the author's biography?".
    • out_of_domain: the user is asking something that is not related to books, the Project Gutenberg or its collection, like harmful requests or "What's the weather like?".
  • messages: the user query, already formatted into a OpenAI's ChatML format for finetuning classification task. The prompt (first message) instructs an LLM to generate a JSON (second message) with the expected intent.

The dataset contains a train and test split, with the following entries per intent class:

Train set counts by intent:

Intent Count
general_questions 86221
novelties 19966
out_of_domain 20057
recommendation 87323
search_author 55998
search_book 87577
search_category 64211

Test set counts by intent:

Intent Count
general_questions 21457
novelties 5013
out_of_domain 5058
recommendation 21959
search_author 13978
search_book 21808
search_category 16066

Dataset Creation

Curation Rationale

The purpose of this dataset is to demonstrate the ability of Smaller Language Models (<1B) to outperform LLMs in specific tasks, while requiring fewer resources and with lower latency.

The goal is to scale better for production ready use cases without compromising quality.

Source Data

The data is built from the combination of two sources:

  • Gutenberg catalog: We downloaded the RDF and CSV offline catalogs provided by the Project Gutenberg.

  • Intent templates: a collection of hand-curated templates associated to an specific intent. The templates may contain {title}, {author} or {category} so that we can generate combinations of those.

Data Collection and Processing

The source data processing is summarized in the following steps:

  • Iterate the catalog and extract the following entities:
    • Author
    • Book titles
    • Categories (subjects)
  • Normalization: clean stopwords, punctuation, remove birth and year dates.
  • Template resolution: for each entity, the following is done:
    • sample a number of templates without replacement. The number of samples is fine-tuned by hand to avoid skew towards a specific intent (e.g. there are twice as many books as authors).
    • format the template(s) with the entity.
    • generate a pair 'intent - query' for each template.

The output of the previous steps is around 1 million pairs. Next, we do the following:

  • Prompt formatting: we format the dataset with the prompt template into ChatML format.
  • Train test split: sampled 40% and 10% for train and test respectively.

Personal and Sensitive Information

The dataset contains purely names from books and titles from the Gutenberg catalog, which are in the public domain. Hence, it doesn't contain any Personal Identifiable Information.

Bias, Risks, and Limitations

The dataset only contains information from books in the public domain. As a rule of thumb, this means that books from 90+ years from 2025 (estimated) will are not represented. A model tuned on this dataset may forget knowledge about more recent titles.

Also, it is tailored towards the Project Gutenberg domain. Hence, it may not generalize well for broader domains.

Acknowledgements

Project Gutenberg volunteers for maintaining the free catalogue; HuggingFace for the dataset hosting.

Downloads last month
40

Models trained or fine-tuned on empathyai/books-intent-dataset