initial add

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.faiss filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

app.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[1]:
+
+
+#import necessary packages
+import os
+from openai import AsyncOpenAI  # importing openai for API usage
+import chainlit as cl  # importing chainlit for our app
+from chainlit.playground.providers import ChatOpenAI  # importing ChatOpenAI tools
+from langchain_community.vectorstores import FAISS
+from langchain_openai import OpenAIEmbeddings
+from langchain.prompts import ChatPromptTemplate
+from operator import itemgetter
+from langchain_core.runnables import RunnablePassthrough
+from langchain_community.vectorstores import FAISS
+from langchain_openai import ChatOpenAI
+from langchain.retrievers import MultiQueryRetriever
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain.chains import create_retrieval_chain
+from langchain import hub
+
+
+
+#from langchain.utils import itemgetter, RunnablePassthrough
+#from langchain.chains import build_chain
+#from langchain.text_splitter import RecursiveCharacterTextSplitter
+#from langchain_community.document_loaders import PyMuPDFLoader
+
+
+# In[2]:
+
+
+#load environment var
+from dotenv import load_dotenv
+load_dotenv()
+
+
+# In[3]:
+
+
+#load in embeddings model
+out_fp = './data'
+embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+#vector_store = FAISS.from_documents(documents, embeddings)
+faiss_fn = 'nvidia_10k_faiss_index.bin'
+vector_store=FAISS.load_local(out_fp+faiss_fn, embeddings, allow_dangerous_deserialization=True)
+retriever = vector_store.as_retriever()
+openai_llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
+
+
+# In[4]:
+
+
+# ChatOpenAI Templates
+template = """Answer the question based only on the following context. If you cannot answer the question with the context, respond with 'I don't know'. You'll get a big bonus and a potential promotion if you provide a high quality answer:
+
+Context:
+{context}
+
+Question:
+{question}
+"""
+prompt_template = ChatPromptTemplate.from_template(template)
+
+
+# In[5]:
+
+
+#create chain
+retrieval_qa_prompt = hub.pull("langchain-ai/retrieval-qa-chat")
+primary_qa_llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
+advanced_retriever = MultiQueryRetriever.from_llm(retriever=retriever, llm=primary_qa_llm)
+document_chain = create_stuff_documents_chain(primary_qa_llm, retrieval_qa_prompt)
+retrieval_chain = create_retrieval_chain(advanced_retriever, document_chain)
+
+
+# In[6]:
+
+
+@cl.on_chat_start  # marks a function that will be executed at the start of a user session
+async def start_chat():
+    settings = {
+        "model": "gpt-3.5-turbo",
+        "temperature": 0,
+        "max_tokens": 250,
+        "top_p": 1,
+        "frequency_penalty": 0,
+        "presence_penalty": 0,
+    }
+
+    cl.user_session.set("settings", settings)
+
+
+# In[8]:
+
+
+@cl.on_message  # marks a function that should be run each time the chatbot receives a message from a user
+async def main(message: cl.Message):
+    settings = cl.user_session.get("settings")
+
+    # Use the retrieval_augmented_qa_chain_openai pipeline with the user's question
+    question = message.content  # Extracting the question from the message content
+    response = retrieval_chain.invoke({"input": question}) # Invoke the pipeline
+    #print(response['answer'])
+    # Extract the response content and context documents
+    response_content = response['answer']
+    #context_documents = '\n'.join([document.page_content for document in response["context"]])
+    #page_numbers = set([document.metadata['page'] for document in response["context"]])
+
+    # Stream the response content back to the user
+    msg = cl.Message(content="")
+    await msg.stream_token(response_content)
+
+
+# In[ ]:
+
+
+
+

chainlit.md

@@ -0,0 +1,14 @@
+# Welcome to Chainlit! 🚀🤖
+
+Hi there, Developer! 👋 We're excited to have you on board. Chainlit is a powerful tool designed to help you prototype, debug and share applications built on top of LLMs.
+
+## Useful Links 🔗
+
+- **Documentation:** Get started with our comprehensive [Chainlit Documentation](https://docs.chainlit.io) 📚
+- **Discord Community:** Join our friendly [Chainlit Discord](https://discord.gg/k73SQ3FyUh) to ask questions, share your projects, and connect with other developers! 💬
+
+We can't wait to see what you create with Chainlit! Happy coding! 💻😊
+
+## Welcome screen
+
+To modify the welcome screen, edit the `chainlit.md` file at the root of your project. If you do not want a welcome screen, just leave this file empty.

datanvidia_10k_faiss_index.bin/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7736d6111b170f0ac1bab605803e524e7a33fbdc123a99fde8366f44b7dfc3
+size 2691117

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.faiss filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,6 @@
+async-openai
+chainlit
+langchain
+faiss
+langchain-openai
+langchain-community