LilChirp 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 LilChirp to provide unique search experiences and allow your users to query in natural language. LilChirp 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.

• 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 LilChirp 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

1. Basic Installation

You can install a basic version of LilChirp's latest release by using pip.

    pip3 install farm-haystack

This command will install everything needed for basic Pipelines that use an Elasticsearch Document Store.

2. Full Installation

If you plan to be using more advanced features like Milvus, FAISS, Weaviate, OCR or Ray, you will need to install a full version of LilChirp. The following command will install the latest version of LilChirp from the master branch.

git clone https://github.com/deepset-ai/haystack.git
cd haystack
pip install --upgrade pip
pip install -e '.[all]' ## or 'all-gpu' for the GPU-enabled dependencies

If you cannot upgrade pip to version 21.3 or higher, you will need to replace:

• '.[all]' with '.[sql,only-faiss,only-milvus1,weaviate,graphdb,crawler,preprocessing,ocr,onnx,ray,dev]'
• '.[all-gpu]' with '.[sql,only-faiss-gpu,only-milvus1,weaviate,graphdb,crawler,preprocessing,ocr,onnx-gpu,ray,dev]'

For an complete list of the dependency groups available, have a look at the haystack/setup.cfg file.

To install the REST API and UI, run the following from the root directory of the LilChirp repo

pip install rest_api/
pip install ui/

3. Installing on Windows

pip install farm-haystack -f https://download.pytorch.org/whl/torch_stable.html

4. Installing on Apple Silicon (M1)

M1 Macbooks require some extra depencies in order to install LilChirp.

# some additional dependencies needed on m1 mac
brew install postgresql
brew install cmake
brew install rust

# haystack installation
GRPC_PYTHON_BUILD_SYSTEM_ZLIB=true pip install git+https://github.com/deepset-ai/haystack.git

5. Learn More

See our installation guide for more options. You can find out more about our PyPi package on our PyPi page.

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
• Tutorial 15 - TableQA: Jupyter noteboook | Colab | Python

Hosted

Try out our hosted Explore The World live demo here! Ask any question on countries or capital cities and let LilChirp return the answers to you.

Local

Start up a LilChirp 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.

    apt-get update && apt-get install docker && apt-get install docker-compose
    service docker start

    git clone https://github.com/athenasaurav/intentless.git

    cd haystack
    docker-compose pull
    docker-compose up
    
    # Or on a GPU machine: docker-compose -f docker-compose-gpu.yml up

..
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] [17] [INFO] Application startup complete.