Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Full Stack application for retrieving Stock Data and News using LLM, LangChain and LangGraph
| Date | Stars |
|---|---|
| 2026-07-31 | 749 |
| 2026-08-01 | 749 |
| 2026-08-02 | 749 |
| 2026-08-06 | 749 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<a rel="license" href="http://creativecommons.org/licenses/by-nc-sa/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by-nc-sa/4.0/88x31.png" /></a><br />This work is licensed under a <a rel="license" href="http://creativecommons.org/licenses/by-nc-sa/4.0/">Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License</a>. # Stock Data Insights Application This project demonstrates the use of Agentic Retrieval-Augmented Generation (RAG) workflows to extract insights from news and financial data pertaining to specific companies and the broader stock market. It leverages Large Language Models (LLMs), ChromaDB as a vector database, LangChain, LangChain Expression Language (LCEL), and LangGraph to provide comprehensive analyses. ## Features - **Stock Performance Visualization**: Displays graphs and charts illustrating the historical performance of selected stocks. - **Attribute-Specific Data Retrieval**: Fetches detailed information related to specific attributes of a particular stock. - **News Aggregation**: Presents general news or topic-specific articles related to a particular stock or company. ## High Level Architecture  ## Approach ### Asynchronous Scraping 1. **News Data**: Asynchronously scrapes news data for a predefined set of stocks at regular intervals, storing the information in MongoDB. The documents are synchronized with ChromaDB to enable LLMs to perform semantic searches, facilitating the retrieval of relevant information specific to a particular stock or company. 2. **Financial Data**: Asynchronously scrapes financial data for selected stocks at regular intervals, storing the information in PostgreSQL. ### LangGraph Workflows #### News Data RAG Graph An Agentic RAG Graph designed to search news data for a stock either in the vector database (synced documents from MongoDB) or perform a web search if relevant documents are not found.  This graph comprises the following nodes: - **Retrieve News from DB (`retrieve_news`)**: Utilizes LLMs, LangChain, and a Retriever Tool to perform semantic searches in the vector database for documents related to a specific stock topic. - **Grade Documents (`grade_documents`)**: Evaluates the quality of documents retrieved in the previous step, assigning a score to determine their relevance. A conditional edge decides whether to generate results or perform an additional web search if the documents are not pertinent. - **Web Search (`web_search`)**: Conducts a web search using TavilySearch tooling integrated with LangChain and LLM calls. - **Generate Results (`generate_results`)**: Produces results based on the user query and the documents retrieved in prior steps. #### Stock Data RAG Graph  An Agentic RAG Graph that searches financial data for a stock in the SQL database (PostgreSQL). This graph includes the following nodes: - **Generate SQL (`generate_sql`)**: Employs LLMs and LangChain to generate an SQL query based on user input. - **Execute SQL (`execute_sql`)**: Executes the SQL query generated in the previous step to fetch data from the database. - **Generate Results (`generate_results`)**: Utilizes LLMs to generate results according to the user query and the data retrieved in the preceding step. #### Stock Data Charts RAG Graph  An Agentic RAG Graph that retrieves financial data for a stock from the SQL database (PostgreSQL) and generates visual charts. This graph consists of the following nodes: - **Generate SQL (`generate_sql`)**: Uses LLMs and LangChain to create an SQL query based on user input. - **Execute SQL (`execute_sql`)**: Runs the SQL query generated earlier to fetch data from the database. ## APIs For detai
Excerpt of 7,908 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:972447f3feabdd52, name:ai agent