AIMLAPI

Call AIMLAPI's OpenAI-compatible chat models from Haystack pipelines and agents.

Amazon Bedrock

Use Models from AI21 Labs, Anthropic, Cohere, Meta, and Amazon via Amazon Bedrock with Haystack

Amazon Sagemaker

Use Models from Huggingface, Anthropic, AI21 Labs, Cohere, Meta, and Amazon via Amazon Sagemaker with Haystack

Anthropic

Use Anthropic Models with Haystack

Apify

Extract data from the web and automate web tasks using Apify-Haystack integration.

Arize Phoenix

Trace your Haystack pipelines with Arize Phoenix

Arize AI

Trace and Monitor your Haystack pipelines with Arize AI

AssemblyAI

Use AssemblyAI transcription, summarization and speaker diarization models with Haystack

AstraDB

A Document Store for storing and retrieval from AstraDB.

Azure AI Search

Use Azure AI Search with Haystack

Azure CosmosDB

Use Azure CosmosDB with Haystack

Azure Document Intelligence

Use Azure Document Intelligence with Haystack

Azure

Use OpenAI models deployed through Azure services with Haystack

Bright Data

Extract data from 45+ websites, get search engine results, and access geo-restricted content using Bright Data's web scraping services.

Browserbase

Use Browserbase headless browsers with Haystack

Burr

Build an agent from Haystack components

Cerebras

Use LLMs served by Cerebras API

Chroma

A Document Store for storing and retrieval from Chroma

Cohere

Use Cohere models with Haystack

Comet API

Use the Comet API for text generation models.

Context AI

A component to log conversations for analytics by Context.ai

Couchbase

Use the Couchbase database with Haystack

DeepEval

Use the DeepEval evaluation framework to calculate model-based metrics

DeepL

Use DeepL translation services with Haystack

Docling

Use Docling to locally parse and chunk PDF, DOCX, and other document types in Haystack

DuckDuckGo

Uses DuckDuckGo API for web searches

Elasticsearch

Use an Elasticsearch database with Haystack

Elevenlabs

ElevenLabs Text-to-Speech components for Haystack.

Exa

Search the web with Exa's AI-powered search, get content, answers, and conduct deep research

FastEmbed

Use the FastEmbed embedding models

fastRAG

fastRAG is a research framework for efficient and optimized retrieval augmented generative pipelines

Featherless AI

Get access to thousands of open source language models hosted by Featherless.ai

Flow Judge

Evaluate Haystack pipelines using Flow Judge

GitHub

Interact with GitHub repositories, issues, and pull requests within Haystack

Google AI

Use Google AI Models with Haystack

Google Gen AI

Use Google's Gemini models with Haystack via the new Google Gen AI SDK

Google Vertex AI

Use Google Vertex AI Models with Haystack

Groq

Use open Language Models served by Groq

HanLP

Use HanLP for Chinese text processing with Haystack

Hugging Face

Use Models on Hugging Face with Haystack

INSTRUCTOR Embedders

A component for computing embeddings using INSTRUCTOR embedding models.

Isaacus

Use the latest foundational legal AI models from Isaacus in Haystack.

Jina AI

Use the latest Jina AI embedding models

LanceDB Haystack

A DocumentStore backed by LanceDB

langfuse

Monitor and trace your Haystack requests.

Llama.cpp

Use Llama.cpp models with Haystack.

Llama Stack

Use the Llama Stack generation models.

llamafile

Run LLMs locally with llamafile

LM Format Enforcer

Use the LM Format Enforcer to enforce JSON Schema / Regex output of your Local Models.

Mastodon Fetcher

A custom component to fetch a mastodon usernames latest posts

Model Context Protocol - MCP

Haystack Tool Integration with the MCP

Llama API

Use Llama Models with Haystack

Milvus

Use the Milvus vector database with Haystack

Mistral

Use the Mistral API for embedding and text generation models.

mixedbread ai

Use mixedbread's models as well as top open-source models in seconds

MongoDB

Use a MongoDB Atlas database with Haystack

MonsterAPI

Use open Language Models served by MonsterAPI

Needle

Use Needle document store and retriever in Haystack.

Neo4j

Use the Neo4j database with Haystack

Notion Extractor

A component to extract pages from Notion to Haystack Documents. Useful for indexing Pipelines.

NVIDIA

Use NVIDIA models with Haystack.

Ollama

Use Ollama models with Haystack. Ollama allows you to get up and running with large language models, locally.

OPEA

Use the OPEA framework for hardware abstraction and orchestration

OpenAI

Use OpenAI Models with Haystack

OpenLIT

Monitor, evaluate & improve GenAI and LLM applications

OpenRouter

Use the OpenRouter API for text generation models.

OpenSearch

A Document Store for storing and retrieval from OpenSearch

OpenStreetMap

Haystack component to fetch geographic data via the freely available OpenStreetMap (OSM) Overpass API.

Opik

Trace and evaluate your Haystack pipelines with Opik

Optimum

High-performance inference using Hugging Face Optimum

PaddleOCR

Use PaddleOCR’s text-recognition and document-parsing capabilities with Haystack

pgvector

A Document Store for storing and retrieval from pgvector

Pinecone

Use a Pinecone database with Haystack

Qdrant

Use the Qdrant vector database with Haystack

Ragas

Use the Ragas evaluation framework to calculate model-based metrics

Ray

Run and scale Haystack Pipelines with Ray in distributed manner

Sambanova

Use open language models served by Sambanova

Serpex

Multi-engine web search for Haystack — access Google, Bing, DuckDuckGo, Brave, Yahoo, and Yandex via Serpex API

SingleStore

Use SingleStore with Haystack

Snowflake

A Snowflake integration that allows table retrieval from a Snowflake database.

STACKIT

Use the STACKIT API for text generation models.

Titan Takeoff Inference Server

Use Titan Takeoff to run local open-source LLMs with Haystack. Titan Takeoff allows you to run the latest models from Meta, Mistral and Alphabet directly in your laptop.

TogetherAI

Use the Together API for text generation models.

Traceloop

Evaluate and monitor the quality of your LLM apps and agents

Trafilatura

Efficiently gather text and metadata on the Web for LLM and RAG

Unstructured File Converter

Component to easily convert files and directories into Documents using the Unstructured API

Valkey

Use a Valkey database with Haystack

vLLM

Use the vLLM inference engine with Haystack

Voyage AI

Use text embeddings and rerankers from Voyage AI

IBM Watsonx

Use IBM’s watsonx models with Haystack via Watsonx SDK.

Weaviate

Use a Weaviate database with Haystack

Weights & Biases Weave Tracer

Send Haystack traces to Weights & Biases for monitoring and visualization