8de1aa3e43
* Remove invalid-envvar-default and logging-too-many-args * Remove import-self, access-member-before-definition and deprecated-argument * Remove used-before-assignment by restructuring type import * Remove unneeded-not * Silence unnecessary-lambda (it's necessary) * Remove pointless-string-statement * Update Documentation & Code Style * Silenced unsupported-membership-test (probably a real bug, can't fix though) * Remove trailing-newlines * Remove super-init-not-called and slience invalid-sequence-index (it's valid) * Remove invalid-envvar-default in ui * Remove some more warnings from pyproject.toml than actually solrted in code, CI will fail * Linting all modules together is more readable * Update Documentation & Code Style * Typo in pylint disable comment * Simplify long boolean statement * Simplify init call in FAISS * Fix inconsistent-return-statements * Fix useless-super-delegation * Fix useless-else-on-loop * Fix another inconsistent-return-statements * Move back pylint disable comment moved by black * Fix consider-using-set-comprehension * Fix another consider-using-set-comprehension * Silence non-parent-init-called * Update pylint exclusion list * Update Documentation & Code Style * Resolve unnecessary-else-after-break * Fix superfluous-parens * Fix no-else-break * Remove is_correctly_retrieved along with its pylint issue * Update exclusions list * Silence constructor issue in squad_data.py (method is already broken) * Fix too-many-return-statements * Fix use-dict-literal * Fix consider-using-from-import and useless-object-inheritance * Update exclusion list * Fix simplifiable-if-statements * Fix one consider-using-dict-items * Fix another consider-using-dict-items * Fix a third consider-using-dict-items * Fix last consider-using-dict-items * Fix three use-a-generator * Silence import errors on numba, tensorboardX and apex, but add comments & logs * Fix couple of mypy issues * Fix another typing issue * Silence mypy, was conflicting with more meaningful pylint issue * Fix no-else-continue * Silence unsubscriptable-object and fix an import error with importlib.metadata * Update Documentation & Code Style * Fix all no-else-raise * Update Documentation & Code Style * Fix inverted parameters in simplified if switch * Change [test] to [all] in some jobs (for typing and linting) * Add comment in haystack/schema.py on pydantic's dataclasses * Move comment from get_documents_by_id into _convert_weaviate_result_to_document in weaviate.py * Add comment on pylint silencing * Fix bug introduced rest_api/controller/search.py * Update Documentation & Code Style * Add ADR about Pydantic dataclasses * Update pydantic-dataclasses.md * Add link to Pydantic docs on Dataclasses 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.
