Skip to content

Additional packages (components, document stores and the likes) to extend the capabilities of Haystack version 2.0 and onwards

License

Notifications You must be signed in to change notification settings

raspawar/haystack-core-integrations

 
 

Repository files navigation

Haystack 2.x Core Integrations

This repository contains integrations to extend the capabilities of Haystack version 2.0 and onwards. The code in this repo is maintained by deepset, see each integration's README file for details around installation, usage and support.

Quick start

You will need hatch to work on or create new integrations, open this link and follow the install instructions for your operating system and platform.

All the integrations are self contained, so the first step before working on one is to cd into the proper folder. For example, to run the tests suite for the Chroma document store, from the root of the repo:

$ cd integrations/chroma
$ hatch run test

Hatch will take care of setting up an isolated Python environment and run the tests.

Please check out our Contribution Guidelines for all the details.

Inventory

License Compliance

Package Type PyPi Package Status
amazon-bedrock-haystack Generator PyPI - Version Test / amazon_bedrock
amazon-sagemaker-haystack Generator PyPI - Version Test / amazon_sagemaker
anthropic-haystack Generator PyPI - Version Test / anthropic
astra-haystack Document Store PyPI - Version Test / astra
chroma-haystack Document Store PyPI - Version Test / chroma
cohere-haystack Embedder, Generator, Ranker PyPI - Version Test / cohere
deepeval-haystack Evaluator PyPI - Version Test / deepeval
elasticsearch-haystack Document Store PyPI - Version Test / elasticsearch
fastembed-haystack Embedder PyPI - Version Test / fastembed
google-ai-haystack Generator PyPI - Version Test / google-ai
google-vertex-haystack Generator PyPI - Version Test / google-vertex
instructor-embedders-haystack Embedder PyPI - Version Test / instructor-embedders
jina-haystack Embedder, Ranker PyPI - Version Test / jina
langfuse-haystack Tracer PyPI - Version Test / langfuse
llama-cpp-haystack Generator PyPI - Version Test / llama-cpp
mistral-haystack Embedder, Generator PyPI - Version Test / mistral
mongodb-atlas-haystack Document Store PyPI - Version Test / mongodb-atlas
nvidia-haystack Generator PyPI - Version Test / nvidia
ollama-haystack Embedder, Generator PyPI - Version Test / ollama
opensearch-haystack Document Store PyPI - Version Test / opensearch
optimum-haystack Embedder PyPI - Version Test / optimum
pinecone-haystack Document Store PyPI - Version Test / pinecone
pgvector-haystack Document Store PyPI - Version Test / pgvector
qdrant-haystack Document Store PyPI - Version Test / qdrant
ragas-haystack Evaluator PyPI - Version Test / ragas
unstructured-fileconverter-haystack File converter PyPI - Version Test / unstructured
uptrain-haystack Evaluator PyPI - Version Staged
weaviate-haystack Document Store PyPI - Version Test / weaviate

Releasing

Note

Only maintainers can release new versions of integrations. If you're a community contributor and want to release a new version of an integration, reach out to a maintainer.

To release a new version of an integration to PyPI tag the commit with the right version number and push the tag to GitHub. The GitHub Actions workflow will take care of the rest.

  1. Tag the commit with the right version number

    The tag needs to have the following format:

    git tag integrations/<INTEGRATION_FOLDER_NAME>-<version>
    

    For example, if we want to release version 1.0.99 of the google-vertex-haystack integration we'd have to push the tag:

    git tag integrations/google_vertex-v1.0.99
    
  2. Push the tag to GitHub

    git push --tags origin
    
  3. Wait for the CI to do its magic

About

Additional packages (components, document stores and the likes) to extend the capabilities of Haystack version 2.0 and onwards

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%