entaoai  by akshata29

LLM app for chatting with enterprise data using OpenAI

created 2 years ago
866 stars

Top 42.3% on sourcepulse

GitHubView on GitHub
Project Summary

This repository provides a framework for building ChatGPT-like experiences over proprietary enterprise data, targeting developers and researchers. It enables users to upload their data and query it using large language models (LLMs) via Azure OpenAI Service, with support for various vector stores like Pinecone, Redis, and Azure Cognitive Search.

How It Works

The core approach leverages Retrieval Augmented Generation (RAG) to ground LLM responses in user-provided data. It supports multiple vector store integrations for efficient data indexing and retrieval. The system is designed to be modular, allowing for the integration of advanced RAG techniques and multi-modal capabilities.

Quick Start & Requirements

  • Installation: Primarily deployed via Azure services (App Service, Azure Functions). Configuration involves setting up Azure OpenAI, a vector store (Pinecone, Redis, or Azure Cognitive Search), and potentially other Azure services like CosmosDB or Azure Speech Services.
  • Dependencies: Azure OpenAI Service, Azure Cognitive Search, Pinecone, Redis, Python, Langchain. Specific API versions for Azure OpenAI (e.g., "2023-07-01-preview" for function calling) may be required.
  • Resources: Requires Azure subscription and configured services. Setup time varies based on familiarity with Azure and chosen vector store.
  • Documentation: Links to architecture, configuration, and workshop notebooks are available within the README.

Highlighted Details

  • Supports multiple vector stores: Pinecone, Redis, Azure Cognitive Search (including hybrid search and re-ranking).
  • Includes advanced RAG techniques and multi-modal RAG patterns.
  • Offers LLM-based evaluation metrics for Q&A systems (Groundedness, Similarity, Coherence, F1 Score).
  • Features include chat with streaming, function calling (weather, stock, Bing search), SQL querying, and summarization.

Maintenance & Community

The project is actively updated, with frequent refactoring and feature additions noted in the README. Contributions are welcomed via pull requests.

Licensing & Compatibility

The README does not explicitly state a license. It mentions being adapted from other repositories, but no specific license information is provided for this project. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project is heavily tied to the Azure ecosystem. Some features are in preview or require specific API versions. The README indicates that certain functionalities (e.g., SEC analysis, PitchBook features) have been moved to separate repositories.

Health Check
Last commit

7 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
7 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.