46 AI tools for LangChain ?
Agentic RAG implements retrieval agents for decision-making on index retrieval, powered by LangGraph.
Build advanced RAG systems with expert design and implementation for document processing, semantic retrieval, and evaluation.
Access and query decentralized subgraphs on The Graph via Playgrounds API. LLM agents can easily leverage blockchain data without wallet or GRT management.
Load data from Apify Actors or Datasets into LlamaIndex.
A LlamaIndex data loader that retrieves documents from Azure Cognitive Search indexes using service credentials and returns them as text.
LlamaIndex reader that retrieves documents from DeepLake datasets using vector similarity search with configurable distance metrics and result limits.
Fetch US company earnings call transcripts from discountingcashflows.com. Not for commercial use.
Elasticsearch Reader for LlamaIndex loads documents from Elasticsearch or Opensearch indexes via REST API, enabling downstream data ingestion and RAG workflows.
Load data from graph databases using Cypher queries. Compatible with Neo4j, AWS Neptune, and Memgraph. Integrates with LlamaIndex and LangChain.
LlamaIndex reader that loads documents from MyScale vector database backends using query vectors and search parameters for semantic retrieval workflows.
Archestra.AI is a centralized MCP orchestrator that provides security, observability, and cost controls for deploying MCP servers organization-wide with
Run your own MCP server on Azure Functions to connect AI agents to real-world APIs. Supports C#, Python, and TypeScript.
Adaptive RAG strategy that unites query analysis with self-corrective RAG.
Corrective RAG (CRAG) is a LangGraph workflow that self-grades retrieved documents for relevance and supplements poor results with web search to improve answer
Implement Corrective RAG (CRAG) with local LLMs and Tavily Search.
Self-RAG enhances RAG with self-reflection and grading for retrieved documents and generations.
Self-RAG workflow using LangGraph that grades retrieved documents and generations for relevance, hallucination detection, and response quality, based on the
Create a product recommendation chatbot using Retrieval Augmented Generation (RAG) with Neo4j graph database and LLMs. Reduce hallucinations and leverage your
End-to-end question answering workflow using Langchain, AnalyticDB vector database, and OpenAI embeddings to build a knowledge base that retrieves context and
A prompt workflow that connects GPT-4 to Pinecone vector database to retrieve relevant context from LangChain documentation, reducing hallucinations by
End-to-end question answering workflow using Langchain, Qdrant vector database, and OpenAI embeddings to build a knowledge base and retrieve contextual answers.
