mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-25 09:50:14 +00:00
fb511dc4a3
* Fix some miscopied code * Remove feedback from the no-answer, seems the backend can't take it * Try to raise concurrent requests per worker * Remove the actual number of workers
111 lines
3.3 KiB
Python
111 lines
3.3 KiB
Python
from typing import List, Dict, Any, Tuple
|
|
|
|
import os
|
|
import logging
|
|
import requests
|
|
from uuid import uuid4
|
|
import streamlit as st
|
|
|
|
|
|
API_ENDPOINT = os.getenv("API_ENDPOINT", "http://localhost:8000")
|
|
STATUS = "initialized"
|
|
HS_VERSION = "hs_version"
|
|
DOC_REQUEST = "query"
|
|
DOC_FEEDBACK = "feedback"
|
|
DOC_UPLOAD = "file-upload"
|
|
|
|
|
|
def haystack_is_ready():
|
|
"""
|
|
Used to show the "Haystack is loading..." message
|
|
"""
|
|
url = f"{API_ENDPOINT}/{STATUS}"
|
|
try:
|
|
if requests.get(url).json():
|
|
return True
|
|
except Exception as e:
|
|
logging.exception(e)
|
|
return False
|
|
|
|
|
|
@st.cache
|
|
def haystack_version():
|
|
"""
|
|
Get the Haystack version from the REST API
|
|
"""
|
|
url = f"{API_ENDPOINT}/{HS_VERSION}"
|
|
return requests.get(url, timeout=0.1).json()["hs_version"]
|
|
|
|
|
|
def query(query, filters={}, top_k_reader=5, top_k_retriever=5) -> Tuple[List[Dict[str, Any]], Dict[str, str]]:
|
|
"""
|
|
Send a query to the REST API and parse the answer.
|
|
Returns both a ready-to-use representation of the results and the raw JSON.
|
|
"""
|
|
|
|
url = f"{API_ENDPOINT}/{DOC_REQUEST}"
|
|
params = {"filters": filters, "Retriever": {"top_k": top_k_retriever}, "Reader": {"top_k": top_k_reader}}
|
|
req = {"query": query, "params": params}
|
|
response_raw = requests.post(url, json=req)
|
|
|
|
if response_raw.status_code >= 400:
|
|
raise Exception(f"{response_raw}")
|
|
|
|
response = response_raw.json()
|
|
if "errors" in response:
|
|
raise Exception(", ".join(response["errors"]))
|
|
|
|
# Format response
|
|
results = []
|
|
answers = response["answers"]
|
|
for answer in answers:
|
|
if answer.get("answer", None):
|
|
results.append(
|
|
{
|
|
"context": "..." + answer["context"] + "...",
|
|
"answer": answer.get("answer", None),
|
|
"source": answer["meta"]["name"],
|
|
"relevance": round(answer["score"] * 100, 2),
|
|
"document": [doc for doc in response["documents"] if doc["id"] == answer["document_id"]][0],
|
|
"offset_start_in_doc": answer["offsets_in_document"][0]["start"],
|
|
"_raw": answer
|
|
}
|
|
)
|
|
else:
|
|
results.append(
|
|
{
|
|
"context": None,
|
|
"answer": None,
|
|
"document": None,
|
|
"relevance": round(answer["score"] * 100, 2),
|
|
"_raw": answer,
|
|
}
|
|
)
|
|
return results, response_raw
|
|
|
|
|
|
def send_feedback(query, answer_obj, is_correct_answer, is_correct_document, document) -> None:
|
|
"""
|
|
Send a feedback (label) to the REST API
|
|
"""
|
|
url = f"{API_ENDPOINT}/{DOC_FEEDBACK}"
|
|
req = {
|
|
"id": str(uuid4()),
|
|
"query": query,
|
|
"document": document,
|
|
"is_correct_answer": is_correct_answer,
|
|
"is_correct_document": is_correct_document,
|
|
"origin": "user-feedback",
|
|
"answer": answer_obj
|
|
}
|
|
response_raw = requests.post(url, json=req)
|
|
if response_raw.status_code >= 400:
|
|
raise ValueError(f"An error was returned [code {response_raw.status_code}]: {response_raw.json()}")
|
|
|
|
|
|
def upload_doc(file):
|
|
url = f"{API_ENDPOINT}/{DOC_UPLOAD}"
|
|
files = [("files", file)]
|
|
response_raw = requests.post(url, files=files).json()
|
|
return response_raw
|