Haystack is an end-to-end framework that enables you to build powerful and production-ready pipelines for different search use cases. Whether you want to perform Question Answering or semantic document search, you can use the State-of-the-Art NLP models in Haystack to provide unique search experiences and allow your users to query in natural language. Haystack is built in a modular fashion so that you can combine the best technology from other open-source projects like Huggingface's Transformers, Elasticsearch, or Milvus.
What to build with Haystack
- Ask questions in natural language and find granular answers in your documents.
- Perform semantic search and retrieve documents according to meaning, not keywords
- Use off-the-shelf models or fine-tune them to your domain.
- Use user feedback to evaluate, benchmark, and continuously improve your live models.
- Leverage existing knowledge bases and better handle the long tail of queries that chatbots receive.
- Automate processes by automatically applying a list of questions to new documents and using the extracted answers.
- Latest models: Utilize all latest transformer-based models (e.g., BERT, RoBERTa, MiniLM) for extractive QA, generative QA, and document retrieval.
- Modular: Multiple choices to fit your tech stack and use case. Pick your favorite database, file converter, or modeling framework.
- Pipelines: The Node and Pipeline design of Haystack allows for custom routing of queries to only the relevant components.
- Open: 100% compatible with HuggingFace's model hub. Tight interfaces to other frameworks (e.g., Transformers, FARM, sentence-transformers)
- Scalable: Scale to millions of docs via retrievers, production-ready backends like Elasticsearch / FAISS, and a fastAPI REST API
- End-to-End: All tooling in one place: file conversion, cleaning, splitting, training, eval, inference, labeling, etc.
- Developer friendly: Easy to debug, extend and modify.
- Customizable: Fine-tune models to your domain or implement your custom DocumentStore.
- Continuous Learning: Collect new training data via user feedback in production & improve your models continuously
|Overview, Components, Guides, API documentation|
|How to install Haystack|
|See what Haystack can do with our Notebooks & Scripts|
|Deploy a Haystack application with Docker Compose and a REST API|
|Slack, Twitter, Stack Overflow, GitHub Discussions|
|We welcome all contributions!|
|Speed & Accuracy of Retriever, Readers and DocumentStores|
|Public roadmap of Haystack|
|Read our articles on Medium|
|We're hiring! Have a look at our open positions|
If you're interested in learning more about Haystack and using it as part of your application, we offer several options.
1. Installing from a package
You can install Haystack by using pip.
pip3 install farm-haystack
Please check our page on PyPi for more information.
2. Installing from GitHub
You can also clone it from GitHub — in case you'd like to work with the master branch and check the latest features:
git clone https://github.com/deepset-ai/haystack.git cd haystack pip install --editable .
To update your installation, do a
git pull. The
--editable flag will update changes immediately.
3. Installing on Windows
On Windows, you might need:
pip install farm-haystack -f https://download.pytorch.org/whl/torch_stable.html
Follow our introductory tutorial to setup a question answering system using Python and start performing queries! Explore the rest of our tutorials to learn how to tweak pipelines, train models and perform evaluation.
- Tutorial 1 - Basic QA Pipeline: Jupyter notebook | Colab | Python
- Tutorial 2 - Fine-tuning a model on own data: Jupyter notebook | Colab | Python
- Tutorial 3 - Basic QA Pipeline without Elasticsearch: Jupyter notebook | Colab | Python
- Tutorial 4 - FAQ-style QA: Jupyter notebook | Colab | Python
- Tutorial 5 - Evaluation of the whole QA-Pipeline: Jupyter noteboook | Colab | Python
- Tutorial 6 - Better Retrievers via "Dense Passage Retrieval": Jupyter noteboook | Colab | Python
- Tutorial 7 - Generative QA via "Retrieval-Augmented Generation": Jupyter noteboook | Colab | Python
- Tutorial 8 - Preprocessing: Jupyter noteboook | Colab | Python
- Tutorial 9 - DPR Training: Jupyter noteboook | Colab | Python
- Tutorial 10 - Knowledge Graph: Jupyter noteboook | Colab | Python
- Tutorial 11 - Pipelines: Jupyter noteboook | Colab | Python
- Tutorial 12 - Long-Form Question Answering: Jupyter noteboook | Colab | Python
- Tutorial 13 - Question Generation: Jupyter noteboook | Colab | Python
- Tutorial 14 - Query Classifier: Jupyter noteboook | Colab | Python
By following these steps, you will start up our demo which creates a Haystack service via Docker Compose. With this you can begin calling it directly via the REST API or even interact with it using the included Streamlit UI.
1. Update/install Docker and Docker Compose, then launch Docker
apt-get update && apt-get install docker && apt-get install docker-compose service docker start
2. Clone Haystack repository
git clone https://github.com/deepset-ai/haystack.git
3. Pull images & launch demo app
cd haystack docker-compose pull docker-compose up # Or on a GPU machine: docker-compose -f docker-compose-gpu.yml up
You should be able to see the following in your terminal window as part of the log output:
.. ui_1 | You can now view your Streamlit app in your browser. .. ui_1 | External URL: http://192.168.108.218:8501 .. haystack-api_1 | [2021-01-01 10:21:58 +0000]  [INFO] Application startup complete.
4. Open the Streamlit UI for Haystack by pointing your browser to the "External URL" from above.
You should see the following:
You can then try different queries against a pre-defined set of indexed articles related to Game of Thrones.
Note: The following containers are started as a part of this demo:
- Haystack API: listens on port 8000
- DocumentStore (Elasticsearch): listens on port 9200
- Streamlit UI: listens on port 8501
Please note that the demo will publish the container ports to the outside world. We suggest that you review the firewall settings depending on your system setup and the security guidelines.