dcarpintero/llamaindexchat
LLM Chatbot w/ Retrieval Augmented Generation using Llamaindex. It demonstrates how to impl. chunking, indexing, and source citation.
Builds a conversational interface with Streamlit that loads documentation from GitHub via LlamaHub's repository loader, chunks content into 1024-token nodes with metadata enrichment, and indexes them with OpenAI embeddings for vector similarity retrieval. Implements Streamlit's caching layer to reduce LLM calls and uses TokenCountingHandler to track prompt/completion tokens for cost estimation, while surfacing retrieved source documents with relevance scores and metadata for answer transparency.
No commits in the last 6 months.
Stars
46
Forks
5
Language
Python
License
—
Category
Last pushed
Oct 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/dcarpintero/llamaindexchat"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ScrapeGraphAI/Scrapegraph-demo
Streamlit demo of Scrapegraph-ai for GPT4-hackaton
pnkvalavala/repochat
Chatbot assistant enabling GitHub repository interaction using LLMs with Retrieval Augmented Generation
run-llama/rags
Build ChatGPT over your data, all with natural language
Caellwyn/long-memory-character-chat
A character chat with integrated medium and long-term memory
Daethyra/FreeStream
Prebuilt Streamlit/LangChain Agent with Tools and Memory