conversational-agent-langchain

![conv](https://socialify.git.ci/mfmezger/conversational-agent-langchain/image?description=1&font=Inter&language=1&name=1&owner=1&pattern=Charlie%20Brown&stargazers=1&theme=Dark)

[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
<a href="https://github.com/psf/black"><img alt="Code style: black" src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
[![prek](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/j178/prek/master/docs/assets/badge-v0.json)](https://github.com/j178/prek)

# Conversational RAG Agent
This is a Rest-Backend for a Conversational Agent, that allows you to embed Documents, search for them using Semantic Search, to QA based on Documents and do document processing with Large Language Models.

![UI](resources/ui.png)


## Table of Contents
- [Conversational RAG Agent](#conversational-rag-agent)
  - [Table of Contents](#table-of-contents)
  - [LLMs and Backend Providers](#llms-and-backend-providers)
  - [Quickstart](#quickstart)
  - [Project Description](#project-description)
  - [What is RAG?](#what-is-rag)
  - [Tracing](#tracing)
  - [Semantic Search](#semantic-search)
    - [Hybrid Search](#hybrid-search)
  - [Architecture](#architecture)
  - [Installation \& Development Backend](#installation--development-backend)
    - [Load Demo Data](#load-demo-data)
  - [Development Frontend](#development-frontend)
  - [Qdrant API Key](#qdrant-api-key)
  - [Testing the API](#testing-the-api)
  - [Star History](#star-history)


## LLMs and Backend Providers

I have decided to stop creating different services for different provider and switching to LiteLLM which allows to use basically every provider you want.

Some providers i would recommend are:

- [Cohere](https://cohere.com/) Awesome models and great free tier.
- [Ollama](https://ollama.com/) If you want to keep your data your data.
- [Google AI Studio](https:/