d470b9d0bd
* Fist attempt at using setup.cfg for dependency management * Trying the new package on the CI and in Docker too * Add composite extras_require * Add the safe_import function for document store imports and add some try-catch statements on rest_api and ui imports * Fix bug on class import and rephrase error message * Introduce typing for optional modules and add type: ignore in sparse.py * Include importlib_metadata backport for py3.7 * Add colab group to extra_requires * Fix pillow version * Fix grpcio * Separate out the crawler as another extra * Make paths relative in rest_api and ui * Update the test matrix in the CI * Add try catch statements around the optional imports too to account for direct imports * Never mix direct deps with self-references and add ES deps to the base install * Refactor several paths in tests to make them insensitive to the execution path * Include tstadel review and re-introduce Milvus1 in the tests suite, to fix * Wrap pdf conversion utils into safe_import * Update some tutorials and rever Milvus1 as default for now, see #2067 * Fix mypy config Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Demo UI
This is a minimal UI that can spin up to test Haystack for your prototypes. It's based on streamlit and is very easy to extend for your purposes.
Usage
Get started with Haystack
The UI interacts with the Haystack REST API. To get started with Haystack please visit the README or checko out our tutorials.
Option 1: Local
Execute in this folder:
streamlit run webapp.py
Requirements: This expects a running Haystack REST API at http://localhost:8000
Option 2: Container
Just run
docker-compose up -d
in the root folder of the Haystack repository. This will start three containers (Elasticsearch, Haystack API, Haystack UI).
You can find the UI at http://localhost:8501
Evaluation Mode
The evaluation mode leverages the feedback REST API endpoint of haystack. The user has the options "Wrong answer", "Wrong answer and wrong passage" and "Wrong answer and wrong passage" to give feedback.
In order to use the UI in evaluation mode, you need an ElasticSearch instance with pre-indexed files and the Haystack REST API. You can set the environment up via docker images. For ElasticSearch, you can check out our documentation and for setting up the REST API this link.
To enter the evaluation mode, select the checkbox "Evaluation mode" in the sidebar. The UI will load the predefined questions from the file eval_lables_examles. The file needs to be prefilled with your data. This way, the user will get a random question from the set and can give his feedback with the buttons below the questions. To load a new question, click the button "Get random question".
The file just needs to have two columns separated by semicolon. You can add more columns but the UI will ignore them. Every line represents a questions answer pair. The columns with the questions needs to be named “Question Text” and the answer column “Answer” so that they can be loaded correctly. Currently, the easiest way to create the file is manully by adding question answer pairs.
The feedback can be exported with the API endpoint export-doc-qa-feedback. To learn more about finetuning a model with user feedback, please check out our docs.
