💼 ChatFinData

This repo is aimed to be an implementation of a locally hosted chatbot specifically focused on question answering over the financial data. Built with LangChain and FastAPI.

✅ Running locally

1. Install dependencies: pip install -r requirements.txt
2. Run the app: make start
   1. To enable tracing, make sure langchain-server is running locally and pass tracing=True to get_chain in main.py. You can find more documentation here.
3. Open localhost:9000 in your browser.

📚 Technical description

There are two components: ingestion and question-answering.

Ingestion has the following steps:

1. Pull pdf from Federal Reserve
2. Load pdf with LangChain's PyPDFLoader Loader
3. Split documents with LangChain's TextSplitter
4. Create a vectorstore of embeddings, using LangChain's vectorstore wrapper (with OpenAI's embeddings and FAISS vectorstore).

Question-Answering has the following steps, all handled by ChatVectorDBChain:

1. Given the chat history and new user input, determine what a standalone question would be (using GPT-3).
2. Given that standalone question, look up relevant documents from the vectorstore.
3. Pass the standalone question and relevant documents to GPT-3 to generate a final answer.

🚀 Roadmap

• Implement LangChain + GPT-3.5 for Federal Speeches application
• Unstructured file access based on langchain
  • [ ].md ?
  • [x].pdf
  • [ ].docx ?
  • [ ].txt ?
• Add support for other LLM models
• Move a vectorstore (chromadb?) to a client/server mode (this offers better performance and scalability than the in-memory mode)
• Implement analysis in time
  • create data structure using time as namespaces?
  • show graphs
  • allign with graphs