mixedbread-ai-langchain 1.0.2

The official Mixedbread AI integration for LangChain.

Mixedbread AI Langchain Integration

Mixedbread AI integration for LangChain. This package provides seamless access to Mixedbread's multimodal AI capabilities, enabling intelligent search that understands meaning across text, images, code, PDFs, and diverse document types. Use our state of the art embedding and reranking models as part of your langchain workflows.

Components

• MixedbreadEmbeddings - State-of-the-art embedding models that generate vectors capturing deep contextual meaning, with full async support and batch processing capabilities for transforming unstructured data into intelligent search
• MixedbreadReranker - Powerful semantic reranking that significantly boosts search relevance by applying sophisticated models to reorder initial search results, essential for optimizing RAG applications and improving precision
• MixedbreadDocumentLoader - Layout-aware document parsing supporting PDF, PPTX, HTML and more formats, providing structured output with detailed content elements for high-quality downstream processing
• MixedbreadVectorStoreRetriever - AI-native search engine that enables conversational queries across multimodal data, supporting millions of documents with natural language understanding across multiple languages.

Installation

pip install mixedbread-ai-langchain

Quick Start

Get your API key from the Mixedbread Platform and set it as an environment variable:

export MXBAI_API_KEY="your-api-key"

Basic Usage

from mixedbread_ai_langchain import MixedbreadEmbeddings

embeddings = MixedbreadEmbeddings(model="mixedbread-ai/mxbai-embed-large-v1")
result = embeddings.embed_query("Who is German and likes bread?")

Async Support

All components support async operations:

import asyncio

async def embed_text():
    embeddings = MixedbreadEmbeddings()
    result = await embeddings.aembed_query("Async embedding example")
    return result

embedding = asyncio.run(embed_text())

Examples

See the examples/ directory for complete usage examples:

• Embeddings - Text and document embedding
• Reranker - Document reranking
• Document Loader - File parsing and loading
• Vector Retriever - Vector-based search

Testing

# Install dev dependencies
pip install -e ".[dev]"

# Run all tests
python run_tests.py all

# Run unit tests only (no API key required)
python run_tests.py unit

# Run integration tests (requires API key)
python run_tests.py integration

# Run specific test files
python run_tests.py tests/test_embeddings.py

Documentation

Learn more at mixedbread.com/docs:

• Embeddings API
• Reranking API
• Parsing API
• Vector Stores API

License

Apache 2.0 License