https://github.com/deepset-ai/hayhooks

Easily deploy Haystack pipelines as REST APIs and MCP Tools.

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
✓
Committers with academic emails
1 of 13 committers (7.7%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (12.3%) to scientific vocabulary

Keywords

ai api api-rest haystack llm mcp mcp-server mcp-tools rest

Keywords from Contributors

agent mlops transformers summarization semantic-search question-answering information-retrieval generative-ai demo-app haystack-ai

Last synced: 4 months ago · JSON representation

Repository

Easily deploy Haystack pipelines as REST APIs and MCP Tools.

Basic Info

Host: GitHub
Owner: deepset-ai
License: apache-2.0
Language: Python
Default Branch: main
Homepage: https://haystack.deepset.ai
Size: 19.4 MB

Statistics

Stars: 116
Watchers: 7
Forks: 32
Open Issues: 16
Releases: 23

Topics

ai api api-rest haystack llm mcp mcp-server mcp-tools rest

Created about 2 years ago · Last pushed 5 months ago

Metadata Files

Readme License

Hayhooks

Hayhooks makes it easy to deploy and serve Haystack Pipelines and Agents.

With Hayhooks, you can:

📦 Deploy your Haystack pipelines and agents as REST APIs with maximum flexibility and minimal boilerplate code.
🛠️ Expose your Haystack pipelines and agents over the MCP protocol, making them available as tools in AI dev environments like Cursor or Claude Desktop. Under the hood, Hayhooks runs as an MCP Server, exposing each pipeline and agent as an MCP Tool.
💬 Integrate your Haystack pipelines and agents with Open WebUI as OpenAI-compatible chat completion backends with streaming support.
🕹️ Control Hayhooks core API endpoints through chat - deploy, undeploy, list, or run Haystack pipelines and agents by chatting with Claude Desktop, Cursor, or any other MCP client.

Documentation

📚 For detailed guides, examples, and API reference, check out our comprehensive documentation.

Quick Start

1. Install Hayhooks

```bash

Install Hayhooks

pip install hayhooks ```

2. Start Hayhooks

bash hayhooks run

3. Create a simple agent

Create a minimal agent wrapper with streaming chat support and a simple HTTP POST API:

```python from typing import AsyncGenerator from haystack.components.agents import Agent from haystack.dataclasses import ChatMessage from haystack.tools import Tool from haystack.components.generators.chat import OpenAIChatGenerator from hayhooks import BasePipelineWrapper, asyncstreaminggenerator

Define a Haystack Tool that provides weather information for a given location.

def weather_function(location): return f"The weather in {location} is sunny."

weathertool = Tool( name="weathertool", description="Provides weather information for a given location.", parameters={ "type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"], }, function=weather_function, )

class PipelineWrapper(BasePipelineWrapper): def setup(self) -> None: self.agent = Agent( chatgenerator=OpenAIChatGenerator(model="gpt-4o-mini"), systemprompt="You're a helpful agent", tools=[weather_tool], )

# This will create a POST /my_agent/run endpoint
# `question` will be the input argument and will be auto-validated by a Pydantic model
async def run_api_async(self, question: str) -> str:
    result = await self.agent.run_async({"messages": [ChatMessage.from_user(question)]})
    return result["replies"][0].text

# This will create an OpenAI-compatible /chat/completions endpoint
async def run_chat_completion_async(
    self, model: str, messages: list[dict], body: dict
) -> AsyncGenerator[str, None]:
    chat_messages = [
        ChatMessage.from_openai_dict_format(message) for message in messages
    ]

    return async_streaming_generator(
        pipeline=self.agent,
        pipeline_run_args={
            "messages": chat_messages,
        },
    )

```

Save as my_agent_dir/pipeline_wrapper.py.

4. Deploy it

bash hayhooks pipeline deploy-files -n my_agent ./my_agent_dir

5. Run it

Call the HTTP POST API (/my_agent/run):

bash curl -X POST http://localhost:1416/my_agent/run \ -H 'Content-Type: application/json' \ -d '{"question": "What can you do?"}'

Call the OpenAI-compatible chat completion API (streaming enabled):

bash curl -X POST http://localhost:1416/chat/completions \ -H 'Content-Type: application/json' \ -d '{ "model": "my_agent", "messages": [{"role": "user", "content": "What can you do?"}] }'

Or integrate it with Open WebUI and start chatting with it!

Key Features

🚀 Easy Deployment

Deploy Haystack pipelines and agents as REST APIs with minimal setup
Support for both YAML-based and wrapper-based pipeline deployment
Automatic OpenAI-compatible endpoint generation

🌐 Multiple Integration Options

MCP Protocol: Expose pipelines as MCP tools for use in AI development environments
Open WebUI Integration: Use Hayhooks as a backend for Open WebUI with streaming support
OpenAI Compatibility: Seamless integration with OpenAI-compatible tools and frameworks

🔧 Developer Friendly

CLI for easy pipeline management
Flexible configuration options
Comprehensive logging and debugging support
Custom route and middleware support

📁 File Upload Support

Built-in support for handling file uploads in pipelines
Perfect for RAG systems and document processing

Next Steps

Quick Start Guide - Get started with Hayhooks
Installation - Install Hayhooks and dependencies
Configuration - Configure Hayhooks for your needs
Examples - Explore example implementations

Community & Support

GitHub: deepset-ai/hayhooks
Issues: GitHub Issues
Documentation: Full Documentation

Hayhooks is actively maintained by the deepset team.

Owner

Name: deepset
Login: deepset-ai
Kind: organization
Email: hello@deepset.ai
Location: Berlin, Germany

Website: https://deepset.ai
Twitter: deepset_ai
Repositories: 14
Profile: https://github.com/deepset-ai

Building enterprise search systems powered by latest NLP & open-source.

GitHub Events

Total

Create event: 71
Release event: 14
Issues event: 73
Watch event: 61
Delete event: 55
Issue comment event: 115
Push event: 214
Pull request review comment event: 169
Pull request event: 118
Pull request review event: 213
Fork event: 16

Last Year

Create event: 71
Release event: 14
Issues event: 73
Watch event: 61
Delete event: 55
Issue comment event: 115
Push event: 214
Pull request review comment event: 169
Pull request event: 118
Pull request review event: 213
Fork event: 16

Committers

Last synced: 5 months ago

All Time

Total Commits: 175
Total Committers: 13
Avg Commits per committer: 13.462
Development Distribution Score (DDS): 0.474

Past Year

Commits: 107
Committers: 4
Avg Commits per committer: 26.75
Development Distribution Score (DDS): 0.14

Top Committers

Name	Email	Commits
Michele Pangrazzi	x**3@g**m	92
Massimiliano Pippi	m**i@g**m	47
anakin87	s**i@g**m	14
Wyatt Cannon	w**n@n**v	5
Rustem Galiullin	r**n@b**i	3
Silvano Cerza	s**a@g**m	3
Bilge Yücel	b**l@d**i	2
Rustem Galiullin	r**l@g**m	2
Vladimir Blagojevic	d**x@g**m	2
alex-stoica	a**a@p**m	2
Alejandro Lazaro	a**n@d**i	1
Alejandro Lazaro	v**t@u**m	1
Sriniketh J	s**7@g**m	1

Committer Domains (Top 20 + Academic)

deepset.ai: 2 bayanat.ai: 1 nasa.gov: 1

Issues and Pull Requests

Last synced: 5 months ago

All Time

Total issues: 64
Total pull requests: 91
Average time to close issues: about 1 month
Average time to close pull requests: 7 days
Total issue authors: 36
Total pull request authors: 15
Average comments per issue: 1.03
Average comments per pull request: 0.43
Merged pull requests: 64
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 38
Pull requests: 69
Average time to close issues: 13 days
Average time to close pull requests: 2 days
Issue authors: 17
Pull request authors: 9
Average comments per issue: 0.76
Average comments per pull request: 0.38
Merged pull requests: 46
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

mpangrazzi (13)
julian-risch (6)
masci (5)
svanschalkwyk (4)
alex-stoica (2)
kkmarv (2)
jacksteussie (2)
anakin87 (2)
GiorgosAlexakis (1)
advin4603 (1)
superkelvint (1)
bmstoyon (1)
whisper-bye (1)
hoschmieder (1)
Shuntw6096 (1)

Pull Request Authors

mpangrazzi (56)
Rusteam (6)
anakin87 (6)
alex-stoica (4)
tellmewyatt (4)
bilgeyucel (3)
ParseDark (2)
srini047 (2)
vblagoje (2)
virtualroot (1)
Yuyang105 (1)
jianjungki (1)
zh4n7wm (1)
MrCatters (1)
lwsinclair (1)

Top Labels

Issue Labels

P1 (4) P2 (3) community-triage (3) P3 (3) enhancement (2) bug (1)

Pull Request Labels

Packages

Total packages: 1
Total downloads:
- pypi 4,730 last-month

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 35
Total maintainers: 1

pypi.org: hayhooks

Grab and deploy Haystack pipelines

Documentation: https://github.com/deepset-ai/hayhooks#readme
License: apache-2.0
Latest release: 1.0.1
published 5 months ago

Versions: 35
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 4,730 Last month

Rankings

Dependent packages count: 10.1%

Average: 38.3%

Dependent repos count: 66.6%

Maintainers (1)

deepset

Last synced: 5 months ago

Dependencies

pyproject.toml pypi

click *
fastapi *
haystack-ai *
python-multipart *
requests *
uvicorn *

.github/workflows/pypi.yml actions

actions/checkout v3 composite

.github/workflows/docker.yml actions

actions/checkout v4 composite
docker/bake-action v4 composite
docker/login-action v3 composite
docker/metadata-action v5 composite
docker/setup-buildx-action v3 composite
docker/setup-qemu-action v3 composite

docker/Dockerfile docker

$base_image latest build
$build_image latest build

https://github.com/deepset-ai/hayhooks

Science Score: 36.0%

Keywords

Keywords from Contributors

Repository

Basic Info

Statistics

Topics

Metadata Files

README.md

Hayhooks

Documentation

Quick Start

1. Install Hayhooks

Install Hayhooks

2. Start Hayhooks

3. Create a simple agent

Define a Haystack Tool that provides weather information for a given location.

4. Deploy it

5. Run it

Key Features

🚀 Easy Deployment

🌐 Multiple Integration Options

🔧 Developer Friendly

📁 File Upload Support

Next Steps

Community & Support

Owner

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: hayhooks

Rankings

Maintainers (1)

Dependencies