LangChain Models - Integração Multi-LLM
04bhavyaa/langchain-models
Integração multi-provider de LLMs e embeddings com LangChain
Ver no GitHubRepositório educacional que demonstra integração de múltiplos modelos de linguagem (OpenAI, Claude, Gemini, Hugging Face) via LangChain. Inclui exemplos práticos de chat models, embeddings e busca semântica de documentos com cosine similarity, facilitando experimentação com diferentes LLMs e vector search.
Instalação
npx convez-ai 04bhavyaa/langchain-models1 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
- Experimentar diferentes modelos de linguagem (OpenAI, Anthropic, Google, Hugging Face)
- Implementar busca semântica de documentos com embeddings
- Construir aplicações de chat com múltiplos provedores
- Prototipagem de sistemas RAG (Retrieval-Augmented Generation)
Veredito

Projeto educacional sólido para aprender integração multi-LLM com LangChain. Bem estruturado com exemplos práticos de chat models e embeddings, ideal para quem quer explorar diferentes provedores sem lock-in. Comunidade amadora, mas código bem documentado.
README
A tradução para o português deste README ainda está na fila.
LangChain Models
This repository contains implementations of various Language Models (LLMs), Chat Models and Embedding Models using LangChain. It demonstrates different model integrations for LLMs and embeddings, including OpenAI, Hugging Face, Google, Sentence Transformers and Anthropic.
📂 Directory Structure
04bhavyaa-langchain-models/
├── README.md # Project documentation
├── requirements.txt # Required dependencies
├── LLMs/
│ └── llm_demo.py # Basic LLM demonstration
├── chat-models/ # Various chat models
│ ├── chatmodel_anthropic.py # Anthropic's Claude integration
│ ├── chatmodel_google.py # Google Gemini (PaLM) integration
│ ├── chatmodel_hf_api.py # Hugging Face API integration
│ ├── chatmodel_hf_local.py # Local Hugging Face LLM integration
│ └── chatmodel_openai.py # OpenAI ChatGPT integration
└── embedding-models/ # Embedding models for similarity search
├── document_similarity.py # Cosine similarity for document search
├── embedding_hf_local.py # Local Hugging Face embeddings
├── embedding_openai_docs.py # OpenAI document embeddings
└── embedding_openai_query.py # OpenAI query embeddings
⚡ Tech Stack
- LangChain (Core framework for chaining LLMs)
- OpenAI API (ChatGPT & Embeddings)
- Anthropic API (Claude models)
- Google Generative AI (Gemini/PaLM models)
- Hugging Face (Transformer-based LLMs & embeddings)
- Scikit-learn (Cosine similarity for document search)
- Pandas & NumPy (Data processing utilities)
🧠 Theory Behind LangChain Models
- LLMs: These are large-scale neural networks trained on vast text corpora. LangChain provides a structured way to interact with them.
- Chat Models: Variants of LLMs optimized for dialogue, such as OpenAI's ChatGPT, Claude, and Gemini.
- Embedding Models: Convert text into high-dimensional vectors to perform similarity search, useful for document retrieval and semantic search.
🔧 Setup Instructions
1. Clone the repository:
git clone https://github.com/yourusername/04bhavyaa-langchain-models.git
cd 04bhavyaa-langchain-models
2. Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
3. Install dependencies:
pip install -r requirements.txt
4. Set Up Environment Variables
Create a .env file and add your API keys:
OPENAI_API_KEY=your_openai_api_key
ANTHROPIC_API_KEY=your_anthropic_api_key
GOOGLE_API_KEY=your_google_api_key
HUGGINGFACEHUB_API_TOKEN=your_huggingface_api_key
5. Run the Models
Example usage for document similarity:
python embedding-models/document_similarity.py
Sample Output:
💡 Contributions are welcome! Feel free to fork, open issues, or submit PRs.