fulviomascara/llamav2_local
Projeto de GenAI usando LLAMA V2 Local estilo ChatPDF
Implements a retrieval-augmented generation (RAG) pipeline using LangChain for semantic document search, ChromaDB for vector storage of PDF embeddings, and Llama 2-Chat (7B-70B parameters) running locally for inference—no external API calls required. Provides a Jupyter notebook workflow that generates sentence embeddings, stores them in a vector database, and surfaces a Gradio web UI for multi-turn conversational interaction with uploaded PDFs.
No commits in the last 6 months.
Stars
61
Forks
25
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/fulviomascara/llamav2_local"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
joelbarranteswins/Platzi-Courses
All the courses which appear here is what I have taken in platzi.com and I own all the files...
ajayarunachalam/gui-pandas-ai
GUIPandasAI - Integrating Generative AI capabilities into Pandas as Web Interface along with...
machinelearningZH/ogd_ai-analyzer
Automagically do a deep check of metadata quality of your DCAT OGD offering.
MarkPhamm/skytrax_reviews
A comprehensive ELT pipeline for analyzing passenger satisfaction data. Features a modern data...
aleeepassarelli/scientific-validation-hub
Um ecossistema open-source para Engenharia Semântica Latente (SLE). Transforme prompts em...