And, believe me, this is ๐ป๐ผ๐ clickbaitโ
GitHub ๐ https://github.com/AstraBert/PapersChat
Demo ๐ as-cle-bert/PapersChat
The app is called ๐๐๐ฉ๐๐ซ๐ฌ๐๐ก๐๐ญ, and it is aimed at ๐บ๐ฎ๐ธ๐ถ๐ป๐ด ๐ฐ๐ต๐ฎ๐๐๐ถ๐ป๐ด ๐๐ถ๐๐ต ๐๐ฐ๐ถ๐ฒ๐ป๐๐ถ๐ณ๐ถ๐ฐ ๐ฝ๐ฎ๐ฝ๐ฒ๐ฟ๐ ๐ฒ๐ฎ๐๐ถ๐ฒ๐ฟ.
๐๐๐ซ๐ ๐ข๐ฌ ๐ฐ๐ก๐๐ญ ๐ญ๐ก๐ ๐๐ฉ๐ฉ ๐๐จ๐๐ฌ:
๐ Parses the papers that you upload thanks to LlamaIndex๐ฆ (either with LlamaParse or with simpler, local methods)
๐ Embeds documents both with a sparse and with a dense encoder to enable hybrid search
๐ Uploads the embeddings to Qdrant
โ๏ธ Activates an Agent based on mistralai/Mistral-Small-24B-Instruct-2501 that will reply to your prompt
๐ง Retrieves information relevant to your question from the documents
๐ง If no relevant information is found, it searches PubMed and arXiv databases
๐ง Returns a grounded answer to your prompt
๐๐จ๐ฐ ๐๐ข๐ ๐ ๐ฆ๐๐ง๐๐ ๐ ๐ญ๐จ ๐ฆ๐๐ค๐ ๐ญ๐ก๐ข๐ฌ ๐๐ฉ๐ฉ๐ฅ๐ข๐๐๐ญ๐ข๐จ๐ง ๐ข๐ง ๐ ๐ก๐จ๐ฎ๐ซ๐ฌ?
Three key points:
- LlamaIndex๐ฆ provides countless integrations with LLM providers, text embedding models and vectorstore services, and takes care of the internal architecture of the Agent. You just plug it in, and it works!๐โก
- Qdrant is a vector database service extremely easy to set up and use: you just need a one-line Docker command๐
- Gradio makes frontend development painless and fast, while still providing modern and responsive interfaces๐๏ธ
And a bonus point:
- Deploying the demo app couldn't be easier if you use Gradio-based Hugging Face Spaces๐ค
So, no more excuses: build your own AI agent today and do it fast, (almost) for free and effortlessly๐
And if you need a starting point, the code for PapersChat is open and fully reproducible on GitHub ๐ https://github.com/AstraBert/PapersChat