mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-25 09:50:14 +00:00

* first draft / notes on new primitives * wip label / feedback refactor * rename doc.text -> doc.content. add doc.content_type * add datatype for content * remove faq_question_field from ES and weaviate. rename text_field -> content_field in docstores. update tutorials for content field * update converters for . Add warning for empty * renam label.question -> label.query. Allow sorting of Answers. * WIP primitives * update ui/reader for new Answer format * Improve Label. First refactoring of MultiLabel. Adjust eval code * fixed workflow conflict with introducing new one (#1472) * Add latest docstring and tutorial changes * make add_eval_data() work again * fix reader formats. WIP fix _extract_docs_and_labels_from_dict * fix test reader * Add latest docstring and tutorial changes * fix another test case for reader * fix mypy in farm reader.eval() * fix mypy in farm reader.eval() * WIP ORM refactor * Add latest docstring and tutorial changes * fix mypy weaviate * make label and multilabel dataclasses * bump mypy env in CI to python 3.8 * WIP refactor Label ORM * WIP refactor Label ORM * simplify tests for individual doc stores * WIP refactoring markers of tests * test alternative approach for tests with existing parametrization * WIP refactor ORMs * fix skip logic of already parametrized tests * fix weaviate behaviour in tests - not parametrizing it in our general test cases. * Add latest docstring and tutorial changes * fix some tests * remove sql from document_store_types * fix markers for generator and pipeline test * remove inmemory marker * remove unneeded elasticsearch markers * add dataclasses-json dependency. adjust ORM to just store JSON repr * ignore type as dataclasses_json seems to miss functionality here * update readme and contributing.md * update contributing * adjust example * fix duplicate doc handling for custom index * Add latest docstring and tutorial changes * fix some ORM issues. fix get_all_labels_aggregated. * update drop flags where get_all_labels_aggregated() was used before * Add latest docstring and tutorial changes * add to_json(). add + fix tests * fix no_answer handling in label / multilabel * fix duplicate docs in memory doc store. change primary key for sql doc table * fix mypy issues * fix mypy issues * haystack/retriever/base.py * fix test_write_document_meta[elastic] * fix test_elasticsearch_custom_fields * fix test_labels[elastic] * fix crawler * fix converter * fix docx converter * fix preprocessor * fix test_utils * fix tfidf retriever. fix selection of docstore in tests with multiple fixtures / parameterizations * Add latest docstring and tutorial changes * fix crawler test. fix ocrconverter attribute * fix test_elasticsearch_custom_query * fix generator pipeline * fix ocr converter * fix ragenerator * Add latest docstring and tutorial changes * fix test_load_and_save_yaml for elasticsearch * fixes for pipeline tests * fix faq pipeline * fix pipeline tests * Add latest docstring and tutorial changes * fix weaviate * Add latest docstring and tutorial changes * trigger CI * satisfy mypy * Add latest docstring and tutorial changes * satisfy mypy * Add latest docstring and tutorial changes * trigger CI * fix question generation test * fix ray. fix Q-generation * fix translator test * satisfy mypy * wip refactor feedback rest api * fix rest api feedback endpoint * fix doc classifier * remove relation of Labels -> Docs in SQL ORM * fix faiss/milvus tests * fix doc classifier test * fix eval test * fixing eval issues * Add latest docstring and tutorial changes * fix mypy * WIP replace dataclasses-json with manual serialization * Add latest docstring and tutorial changes * revert to dataclass-json serialization for now. remove debug prints. * update docstrings * fix extractor. fix Answer Span init * fix api test * keep meta data of answers in reader.run() * fix meta handling * adress review feedback * Add latest docstring and tutorial changes * make document=None for open domain labels * add import * fix print utils * fix rest api * adress review feedback * Add latest docstring and tutorial changes * fix mypy Co-authored-by: Markus Paff <markuspaff.mp@gmail.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
74 lines
2.2 KiB
Python
74 lines
2.2 KiB
Python
import os
|
|
|
|
import logging
|
|
import requests
|
|
import streamlit as st
|
|
from haystack import Answer
|
|
|
|
API_ENDPOINT = os.getenv("API_ENDPOINT", "http://localhost:8000")
|
|
STATUS = "initialized"
|
|
DOC_REQUEST = "query"
|
|
DOC_FEEDBACK = "feedback"
|
|
DOC_UPLOAD = "file-upload"
|
|
|
|
|
|
def haystack_is_ready():
|
|
url = f"{API_ENDPOINT}/{STATUS}"
|
|
try:
|
|
if requests.get(url).json():
|
|
return True
|
|
except Exception as e:
|
|
logging.exception(e)
|
|
return False
|
|
|
|
|
|
@st.cache(show_spinner=False)
|
|
def retrieve_doc(query, filters=None, top_k_reader=5, top_k_retriever=5):
|
|
# Query Haystack API
|
|
url = f"{API_ENDPOINT}/{DOC_REQUEST}"
|
|
params = {"filters": filters, "ESRetriever": {"top_k": top_k_retriever}, "Reader": {"top_k": top_k_reader}}
|
|
req = {"query": query, "params": params}
|
|
response_raw = requests.post(url, json=req).json()
|
|
|
|
# Format response
|
|
result = []
|
|
answers: List[Answer] = response_raw["answers"]
|
|
for i in range(len(answers)):
|
|
answer = answers[i]["answer"]
|
|
if answer:
|
|
result.append(
|
|
{
|
|
"context": "..." + answer.context + "...",
|
|
"answer": answer,
|
|
"source": answer.meta["name"],
|
|
"relevance": round(answer.score * 100, 2),
|
|
"document_id": answer.document_id,
|
|
"offset_start_in_doc": answer.offsets_in_document[0].start,
|
|
}
|
|
)
|
|
return result, response_raw
|
|
|
|
|
|
def feedback_doc(question, is_correct_answer, document_id, model_id, is_correct_document, answer, offset_start_in_doc):
|
|
# Feedback Haystack API
|
|
url = f"{API_ENDPOINT}/{DOC_FEEDBACK}"
|
|
#TODO adjust after Label refactoring
|
|
req = {
|
|
"question": question,
|
|
"is_correct_answer": is_correct_answer,
|
|
"document_id": document_id,
|
|
"model_id": model_id,
|
|
"is_correct_document": is_correct_document,
|
|
"answer": answer,
|
|
"offset_start_in_doc": offset_start_in_doc,
|
|
}
|
|
response_raw = requests.post(url, json=req).json()
|
|
return response_raw
|
|
|
|
|
|
def upload_doc(file):
|
|
url = f"{API_ENDPOINT}/{DOC_UPLOAD}"
|
|
files = [("files", file)]
|
|
response_raw = requests.post(url, files=files).json()
|
|
return response_raw
|