# paulpierre/RasaGPT

💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram

Repository: https://github.com/paulpierre/RasaGPT
Canonical: https://ross.abutalabs.com/products/rasagpt
Homepage: https://rasagpt.dev
Language: Python
License: MIT
License Family: permissive
Topics: ai, chatbot, fastapi, gpt-3, gpt-4, langchain, llama-index, llm, ml, openai, rasa, rasa-chatbot, rasa-core, rasa-nlu, telegram, telegram-bot, chatgpt
Last push: 2025-11-12T14:43:36+00:00

## Health v2 (maintenance only)
Score: 53/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 51, release rhythm 35, longevity 87
- inputs: {"age_days": 1226, "days_push": 294, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2462, forks 250 (observed 2026-08-28T04:06:53.523176+00:00)

## What it is
RasaGPT is a headless LLM chatbot platform built on top of Rasa and Langchain, serving as a boilerplate and reference implementation. It integrates Rasa with Telegram, FastAPI, LlamaIndex, and pgvector to provide document upload, indexing, retrieval, and context injection for LLM-powered conversations.

## Use cases
- build a telegram chatbot powered by gpt-4
- integrate langchain with rasa for retrieval-augmented conversations
- create a headless llm chatbot api with fastapi
- index documents and inject context into chatbot responses with pgvector
- add multi-tenancy to a rasa chatbot deployment
- self-host a chatgpt-like assistant on telegram

## When to choose
- you want a working reference implementation combining Rasa, Langchain, and Telegram
- you need document upload and RAG-style context injection in a chatbot
- you need multi-tenancy and custom pgvector schemas that Rasa does not natively support
- you want a dockerized starting point including macOS Apple Silicon support

## When to avoid
- you need production-grade security - the project admits prompt injection and security vulnerabilities
- you want a maintained, stable product rather than a boilerplate/reference implementation
- you do not use Rasa or Telegram in your stack
- you need a fully managed chatbot platform without self-hosting

## Facets
- artifact type: framework
- maturity: experimental
- function: chatbot, rag, agent-framework, nlp, api-framework, web-framework, vector-database, llm-inference
- domain: chatbots, large-language-models, artificial-intelligence, messaging-platforms, developer-tools
- platform: python, self-hosted, cross-platform
- tags: rasa, langchain, llama-index, pgvector, fastapi, telegram-bot, headless-chatbot, boilerplate, gpt-4, openai, retrieval-augmented-generation, natural-language-processing, docker, telegram

## Member repositories
- paulpierre/RasaGPT (main) score 53

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:53.523176+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:29:18.664218+00:00, confidence not recorded.
  - readme: https://github.com/paulpierre/RasaGPT (fetched 2026-08-28T04:06:53.523176+00:00, sha 317c7c617e42)
- Data as of 2026-08-30T08:39:29.467469+00:00.