ChatwithPDF
sagnik-datta-02/ChatwithPDF
Converse com seus PDFs usando RAG e Claude 3
Ver no GitHubPlugin RAG que permite conversa interativa com documentos PDF usando Langchain e Claude 3 como LLM. Extrai texto, cria índices vetoriais com FAISS e responde perguntas sobre o conteúdo dos PDFs através de uma interface Streamlit.
Instalação
npx convez-ai sagnik-datta-02/ChatwithPDF1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Análise e resumo de documentos extensos
- Pesquisa e extração de informações em PDFs
- Atendimento ao cliente baseado em documentação
Veredito

Solução prática e bem implementada para RAG com PDFs, aproveitando bem o stack Langchain + Claude + FAISS. Ideal para quem precisa consultar documentos via chat conversacional, mas requer Streamlit como dependência e API key do Anthropic.
README
A tradução para o português deste README ainda está na fila.
RAG-based Chat with PDF
This project enables conversational interaction with PDF documents using the Retrieval-Augmented Generation (RAG) model. Users can ask questions related to the content of uploaded PDF files, and the system will provide detailed responses using RAG-based conversation generation techniques.
Features
-
PDF Upload: Users can upload one or multiple PDF files containing the information they want to inquire about.
-
Text Extraction: Extracts text content from uploaded PDF files for processing and analysis.
-
Text Chunking: Splits the extracted text into smaller chunks for efficient processing and retrieval.
-
Vector Store Creation: Utilizes FAISS to create a vector store from the text chunks, enabling fast and accurate retrieval of relevant information.
-
Conversational Interface: Utilizes the RAG model to generate responses to user queries in a conversational manner.
Tech Stack
- Python: Programming language used for development.
- Streamlit: Web application framework for building interactive web applications.
- PyPDF2: Python library for reading PDF files.
- Langchain: Framework for developing RAG model using LLM.
- FAISS: Library for efficient similarity search and clustering of dense vectors.
- Anthropic: API for claude-3-sonnet-20240229 LLM.
Installation
To run this project locally, follow these steps:
- Clone the repository:
git clone https://github.com/sagnik-datta-02/ChatwithPDF.git
- Install the required dependencies:
pip install -r requirements.txt
-
Set up environment variables:
-
Ensure you have an Anthropic API key and set it in your environment variables as
ANTHROPIC_API_KEY. -
Make sure to have a
.envfile containing your environment variables, including the Anthropic API key.
-
-
Run the Streamlit app:
streamlit run multipdfragapp.py
Usage
- Upload PDF files containing the information you want to inquire about.
- Click on "Submit & Process" to process the uploaded PDF files.
- Ask a question related to the content of the uploaded PDF files in the text input field and receive a response to your question.
License
This project is licensed under the MIT License - see the LICENSE file for details.