mirror of
https://github.com/qdrant/landing_page.git
synced 2026-10-04 10:28:29 +02:00
initial commit; Claude generated SEO descriptions
This commit is contained in:
kanungle
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Frameworks
|
||||
short_description: "Browse Qdrant integrations with AI agent frameworks, RAG libraries, evaluation tools, and orchestration platforms across Python, TypeScript, Java, Rust, and more."
|
||||
description: "Explore Qdrant integrations with AI frameworks for agents, RAG, evaluation, and orchestration, including LangChain, LlamaIndex, Haystack, CrewAI, and many others."
|
||||
weight: 800
|
||||
partition: ecosystem
|
||||
aliases: ["/documentation/frameworks/memgpt/"]
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Agno
|
||||
short_description: "Power Agno multi-agent systems with Qdrant as the vector knowledge base for fast retrieval, memory, and tool-augmented agent workflows."
|
||||
description: "Use Qdrant as the knowledge base for Agno multi-agent systems to give agents persistent memory and fast retrieval over documents and external data."
|
||||
---
|
||||
|
||||
# Agno
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: AutoGen
|
||||
short_description: "Build multi-agent RetrieveChat workflows with Microsoft AutoGen and Qdrant, giving cooperating agents fast vector search over your documents."
|
||||
description: "Use Microsoft AutoGen with Qdrant to build multi-agent RAG workflows where cooperating LLM agents retrieve and reason over documents stored as vectors."
|
||||
aliases: [ ../integrations/autogen/ ]
|
||||
---
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: CamelAI
|
||||
short_description: "Use Qdrant as the vector storage backend in CAMEL-AI to ingest, retrieve, and reason over data inside LLM-based agents."
|
||||
description: "Integrate Qdrant with CAMEL-AI as the vector storage backend for agent memory and retrieval, powering LLM agents that solve real-world tasks with grounded data."
|
||||
---
|
||||
|
||||
# Camel
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Cheshire Cat
|
||||
short_description: "Run Cheshire Cat agents on Qdrant as the default vector memory, taking advantage of collection aliases, quantization, and snapshots."
|
||||
description: "Use Qdrant as the vector memory for Cheshire Cat agents, with built-in support for aliases, quantization, and snapshots for fast and durable retrieval."
|
||||
aliases: [ ../integrations/cheshire-cat/ ]
|
||||
---
|
||||
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
---
|
||||
title: "Cognee"
|
||||
short_description: "Pair Qdrant's vector breadth with Cognee's graph precision to give agents semantic memory grounded in entities, relationships, and time."
|
||||
description: Cognee ships a Qdrant adapter and documents Qdrant as a preferred, built-in vector database option. That means you configure one URI and key, and Cognee's pipelines will read/write embeddings directly to Qdrant while building and querying the graph.
|
||||
---
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: CrewAI
|
||||
short_description: "Back CrewAI's short-term and entity memory with Qdrant so role-playing agents can recall context, relationships, and past interactions reliably."
|
||||
description: "Use Qdrant as the memory store for CrewAI agents, powering short-term and entity memory with vector search for richer multi-agent collaboration."
|
||||
---
|
||||
|
||||
# CrewAI
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Dagster
|
||||
short_description: "Orchestrate AI data pipelines in Dagster with the Qdrant resource to ingest, embed, and query vector collections from declarative assets."
|
||||
description: "Use the Qdrant Dagster integration to build observable AI data pipelines that ingest documents, manage collections, and run vector search from Dagster assets."
|
||||
---
|
||||
|
||||
# Dagster
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: DeepEval
|
||||
short_description: "Evaluate Qdrant-backed RAG pipelines with DeepEval, scoring answer relevancy, faithfulness, hallucination, and contextual precision against your retrieval results."
|
||||
description: "Use DeepEval to test Qdrant-powered RAG pipelines, measuring answer relevancy, faithfulness, hallucination, and contextual precision over retrieved vector results."
|
||||
---
|
||||
|
||||
# DeepEval
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Stanford DSPy
|
||||
short_description: "Use Qdrant as the retrieval model in Stanford DSPy programs to ground prompting, reasoning, and self-improving LLM pipelines in your data."
|
||||
description: "Configure DSPy to use Qdrant as its retrieval model, grounding declarative LLM programs and RAG modules in fast vector search over your collections."
|
||||
aliases: [ ../integrations/dspy/ ]
|
||||
---
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Dynamiq
|
||||
short_description: "Add Qdrant as a writer, retriever, or agent memory inside Dynamiq Gen AI workflows to orchestrate RAG and tool-using LLM agents."
|
||||
description: "Use Qdrant in Dynamiq Gen AI workflows for document writing, retrieval, and agent memory to power RAG pipelines and tool-augmented LLM agents."
|
||||
---
|
||||
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Feast
|
||||
short_description: "Use Qdrant as the online vector store in Feast to serve embedding features and similarity lookups in production ML systems at scale."
|
||||
description: "Configure Qdrant as the online vector store in the Feast feature store to serve embedding features and similarity searches for production ML systems."
|
||||
---
|
||||
|
||||
## Feast
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: FiftyOne
|
||||
short_description: "Run image and text similarity search over computer vision datasets in FiftyOne, backed by Qdrant for fast vector retrieval."
|
||||
description: "Use Qdrant with FiftyOne to power image and text similarity search across computer vision datasets and improve dataset quality and model insights."
|
||||
aliases: [ ../integrations/fifty-one ]
|
||||
---
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Firebase Genkit
|
||||
short_description: "Build production AI apps with Firebase Genkit using Qdrant for indexing and semantic retrieval via the official Qdrant Genkit plugin."
|
||||
description: "Use the Qdrant Genkit plugin to add semantic retrieval and indexing to Firebase Genkit AI apps, with configurable embedders and collection options."
|
||||
---
|
||||
|
||||
# Firebase Genkit
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Google ADK
|
||||
short_description: "Connect Google Agent Development Kit agents to Qdrant via the Qdrant MCP Server for semantic memory, retrieval, and tool-augmented reasoning."
|
||||
description: "Use Qdrant with Google ADK agents through the Qdrant MCP Server, giving agents semantic memory and retrieval tools for storing and recalling information."
|
||||
---
|
||||
|
||||
# Google ADK
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Haystack
|
||||
short_description: "Build generative AI, QA, and semantic search systems in Haystack with the Qdrant document store, including support for quantization and advanced indexing."
|
||||
description: "Use the Qdrant document store with Haystack to build generative AI, QA, and semantic search pipelines with full control over collection and quantization options."
|
||||
aliases:
|
||||
- ../integrations/haystack/
|
||||
- /documentation/overview/integrations/haystack/
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: HoneyHive
|
||||
short_description: "Trace and evaluate Qdrant-powered RAG pipelines in HoneyHive to monitor latency, retrieval quality, and embedding performance in production."
|
||||
description: "Use HoneyHive to trace and evaluate Qdrant vector search in RAG pipelines, monitoring latency, retrieval relevance, and embedding quality at scale."
|
||||
---
|
||||
|
||||
# HoneyHive
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: AWS Lakechain
|
||||
short_description: "Stream document embeddings from AWS Project Lakechain pipelines into Qdrant collections using the Qdrant storage connector and AWS CDK."
|
||||
description: "Deploy AWS document processing pipelines with Project Lakechain that write embeddings into Qdrant collections via the Qdrant storage connector and CDK."
|
||||
---
|
||||
|
||||
# AWS Lakechain
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: LangChain
|
||||
short_description: "Build LangChain apps with Qdrant as the vector store, supporting dense, sparse, and hybrid retrieval for semantic search and RAG."
|
||||
description: "Use the LangChain Qdrant integration to power semantic search and RAG with dense, sparse, and hybrid retrieval over your documents and embeddings."
|
||||
aliases:
|
||||
- ../integrations/langchain/
|
||||
- /documentation/overview/integrations/langchain/
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: LangChain4j
|
||||
short_description: "Use Qdrant as the embedding store in LangChain4j to build context-aware AI applications in Java with full semantic retrieval support."
|
||||
description: "Integrate Qdrant with LangChain4j as the embedding store for Java AI apps, powering retrieval-augmented generation and semantic search over your data."
|
||||
---
|
||||
|
||||
# LangChain for Java
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: LangGraph
|
||||
short_description: "Add Qdrant retrieval nodes to LangGraph workflows in Python or JavaScript to ground stateful, multi-actor agent applications in your data."
|
||||
description: "Use Qdrant retrieval tools in LangGraph workflows to build stateful, multi-actor agents that combine LangChain components with hybrid vector search."
|
||||
aliases: [ ../integrations/langgraph/ ]
|
||||
---
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: LlamaIndex
|
||||
short_description: "Index and retrieve private data in LlamaIndex with Qdrant as the vector store, augmenting LLMs with grounded context from your documents."
|
||||
description: "Use Qdrant as the vector store in LlamaIndex to ingest private data and augment LLM apps with semantic retrieval and retrieval-augmented generation."
|
||||
aliases:
|
||||
- ../integrations/llama-index/
|
||||
- /documentation/overview/integrations/llama-index/
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Mastra
|
||||
short_description: "Add Qdrant as the vector store in Mastra TypeScript AI apps to power RAG, agents, workflows, and evaluations on local or serverless deployments."
|
||||
description: "Use Qdrant with the Mastra TypeScript framework as the vector store for RAG, agents, and workflows running locally or in serverless cloud environments."
|
||||
---
|
||||
|
||||
# Mastra
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Mem0
|
||||
short_description: "Power Mem0's self-improving memory layer with Qdrant to give chatbots and AI assistants personalized, long-lasting recall of user preferences."
|
||||
description: "Configure Mem0 to use Qdrant as its vector store backend, giving LLM applications a self-improving memory layer with personalized, long-term user recall."
|
||||
---
|
||||
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Microsoft GraphRAG
|
||||
short_description: "Plug Qdrant in as a custom vector store for Microsoft GraphRAG to combine knowledge-graph indexing with fast vector retrieval."
|
||||
description: "Use Qdrant as a custom vector store backend for Microsoft GraphRAG to combine graph-based indexing with high-performance vector search for grounded LLM responses."
|
||||
---
|
||||
|
||||
# Microsoft GraphRAG
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: VectaX - Mirror Security
|
||||
short_description: "Secure vector search in Qdrant with Mirror Security VectaX — encrypt embeddings and enforce role-based access on similarity queries."
|
||||
description: "Combine Mirror Security VectaX with Qdrant to encrypt vector embeddings and enforce role-based access control on semantic search and retrieval."
|
||||
---
|
||||
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Neo4j GraphRAG
|
||||
short_description: "Run GraphRAG with Neo4j and Qdrant — vector search in Qdrant retrieves candidates that the Neo4j knowledge graph turns into grounded answers."
|
||||
description: "Use the Neo4j GraphRAG package with Qdrant as a vector retriever to combine graph-based knowledge with fast vector search for retrieval-augmented generation."
|
||||
---
|
||||
|
||||
# Neo4j GraphRAG
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Microsoft NLWeb
|
||||
short_description: "Add natural language interfaces to websites with Microsoft NLWeb backed by Qdrant as the vector store for embedding storage and context retrieval."
|
||||
description: "Use Microsoft NLWeb with Qdrant as the retrieval engine to build natural language interfaces for websites, powered by Schema.org, RSS, and the MCP protocol."
|
||||
---
|
||||
|
||||
# NLWeb
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Rig-rs
|
||||
short_description: "Build scalable LLM apps in Rust with Rig and use Qdrant as the vector store for semantic ingestion, retrieval, and RAG workflows."
|
||||
description: "Use Rig with Qdrant in Rust to build modular LLM applications with semantic retrieval, ingesting documents and querying them through the Qdrant vector store."
|
||||
---
|
||||
|
||||
# Rig-rs
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Semantic-Router
|
||||
short_description: "Route LLM and agent requests by semantic meaning using Semantic-Router with Qdrant as the vector index for fast, embedding-based decisions."
|
||||
description: "Use Semantic-Router with Qdrant as the vector index to make decision-layer routing for LLM agents based on semantic similarity rather than LLM generations."
|
||||
---
|
||||
|
||||
# Semantic-Router
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: SmolAgents
|
||||
short_description: "Pair Hugging Face SmolAgents with Qdrant retrieval to build code-writing agents that query vector collections through reusable tools."
|
||||
description: "Build Hugging Face SmolAgents that call Qdrant retrieval tools to query vector collections, combining code-driven agents with semantic search over your data."
|
||||
---
|
||||
|
||||
# SmolAgents
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Spring AI
|
||||
short_description: "Add Qdrant as the vector store in Spring AI Java apps to power semantic search and RAG with Spring Boot configuration and starter packages."
|
||||
description: "Use Qdrant as the vector store in Spring AI to build Java AI apps with Spring-friendly abstractions for embeddings, semantic search, and RAG pipelines."
|
||||
---
|
||||
|
||||
# Spring AI
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Swiftide
|
||||
short_description: "Build streaming indexing and querying pipelines in Rust with Swiftide using Qdrant as the vector store for dense and hybrid retrieval."
|
||||
description: "Use Swiftide with Qdrant in Rust to build streaming indexing and querying pipelines for LLM apps, supporting dense and hybrid sparse/dense vector search."
|
||||
---
|
||||
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Sycamore
|
||||
short_description: "Process complex unstructured documents with Sycamore and write or read embeddings against Qdrant collections for GenAI and RAG analytics."
|
||||
description: "Use the Sycamore Qdrant connector to write and read embeddings for PDFs, HTML, and other unstructured documents, powering GenAI, RAG, and document analytics."
|
||||
---
|
||||
|
||||
## Sycamore
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Testcontainers
|
||||
short_description: "Spin up disposable Qdrant instances inside integration tests with Testcontainers modules for Java, Go, Node.js, Python, and .NET."
|
||||
description: "Use Testcontainers to launch disposable Qdrant instances for end-to-end integration tests across Java, Go, Node.js, Python, and .NET projects."
|
||||
aliases: [ ../infrastructure/testcontainers/ ]
|
||||
---
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: txtai
|
||||
short_description: "Use Qdrant as the embedding backend for txtai semantic applications, powering similarity search over Transformer-based neural embeddings."
|
||||
description: "Configure txtai to use Qdrant as its embedding backend, building semantic search apps over Transformer-based neural embeddings with high-performance vector search."
|
||||
aliases: [ ../integrations/txtai/ ]
|
||||
---
|
||||
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: Vanna.AI
|
||||
short_description: "Train Vanna.AI text-to-SQL agents with Qdrant as the RAG vector store to generate accurate SQL queries grounded in your database schema and docs."
|
||||
description: "Use Qdrant as the vector store for Vanna.AI text-to-SQL agents, training RAG models on schema and documentation to generate accurate SQL for your database."
|
||||
---
|
||||
|
||||
# Vanna.AI
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
---
|
||||
title: VoltAgent
|
||||
short_description: "Build TypeScript AI agents with VoltAgent and Qdrant retrieval, using the framework's observability dashboard to monitor agent actions and tool calls."
|
||||
description: "Use VoltAgent with Qdrant retrievers to build observable TypeScript AI agents, combining modular tool integration with semantic search over your knowledge base."
|
||||
---
|
||||
|
||||
# VoltAgent
|
||||
|
||||
Reference in New Issue
Block a user