mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-07-23 08:52:16 +00:00

* 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>
280 lines
11 KiB
Python
280 lines
11 KiB
Python
import os
|
|
import sys
|
|
import logging
|
|
import pandas as pd
|
|
from json import JSONDecodeError
|
|
from pathlib import Path
|
|
import streamlit as st
|
|
from annotated_text import annotation
|
|
from markdown import markdown
|
|
|
|
from ui.utils import haystack_is_ready, query, send_feedback, upload_doc, haystack_version, get_backlink
|
|
|
|
|
|
# Adjust to a question that you would like users to see in the search bar when they load the UI:
|
|
DEFAULT_QUESTION_AT_STARTUP = os.getenv("DEFAULT_QUESTION_AT_STARTUP", "What's the capital of France?")
|
|
DEFAULT_ANSWER_AT_STARTUP = os.getenv("DEFAULT_ANSWER_AT_STARTUP", "Paris")
|
|
|
|
# Sliders
|
|
DEFAULT_DOCS_FROM_RETRIEVER = int(os.getenv("DEFAULT_DOCS_FROM_RETRIEVER", "3"))
|
|
DEFAULT_NUMBER_OF_ANSWERS = int(os.getenv("DEFAULT_NUMBER_OF_ANSWERS", "3"))
|
|
|
|
# Labels for the evaluation
|
|
EVAL_LABELS = os.getenv("EVAL_FILE", str(Path(__file__).parent / "eval_labels_example.csv"))
|
|
|
|
# Whether the file upload should be enabled or not
|
|
DISABLE_FILE_UPLOAD = bool(os.getenv("DISABLE_FILE_UPLOAD"))
|
|
|
|
|
|
def set_state_if_absent(key, value):
|
|
if key not in st.session_state:
|
|
st.session_state[key] = value
|
|
|
|
|
|
def main():
|
|
|
|
st.set_page_config(page_title="Haystack Demo", page_icon="https://haystack.deepset.ai/img/HaystackIcon.png")
|
|
|
|
# Persistent state
|
|
set_state_if_absent("question", DEFAULT_QUESTION_AT_STARTUP)
|
|
set_state_if_absent("answer", DEFAULT_ANSWER_AT_STARTUP)
|
|
set_state_if_absent("results", None)
|
|
set_state_if_absent("raw_json", None)
|
|
set_state_if_absent("random_question_requested", False)
|
|
|
|
# Small callback to reset the interface in case the text of the question changes
|
|
def reset_results(*args):
|
|
st.session_state.answer = None
|
|
st.session_state.results = None
|
|
st.session_state.raw_json = None
|
|
|
|
# Title
|
|
st.write("# Haystack Demo - Explore the world")
|
|
st.markdown(
|
|
"""
|
|
This demo takes its data from a selection of Wikipedia pages crawled in November 2021 on the topic of
|
|
|
|
<h3 style='text-align:center;padding: 0 0 1rem;'>Countries and capital cities</h3>
|
|
|
|
Ask any question on this topic and see if Haystack can find the correct answer to your query!
|
|
|
|
*Note: do not use keywords, but full-fledged questions.* The demo is not optimized to deal with keyword queries and might misunderstand you.
|
|
""",
|
|
unsafe_allow_html=True,
|
|
)
|
|
|
|
# Sidebar
|
|
st.sidebar.header("Options")
|
|
top_k_reader = st.sidebar.slider(
|
|
"Max. number of answers",
|
|
min_value=1,
|
|
max_value=10,
|
|
value=DEFAULT_NUMBER_OF_ANSWERS,
|
|
step=1,
|
|
on_change=reset_results,
|
|
)
|
|
top_k_retriever = st.sidebar.slider(
|
|
"Max. number of documents from retriever",
|
|
min_value=1,
|
|
max_value=10,
|
|
value=DEFAULT_DOCS_FROM_RETRIEVER,
|
|
step=1,
|
|
on_change=reset_results,
|
|
)
|
|
eval_mode = st.sidebar.checkbox("Evaluation mode")
|
|
debug = st.sidebar.checkbox("Show debug info")
|
|
|
|
# File upload block
|
|
if not DISABLE_FILE_UPLOAD:
|
|
st.sidebar.write("## File Upload:")
|
|
data_files = st.sidebar.file_uploader("", type=["pdf", "txt", "docx"], accept_multiple_files=True)
|
|
for data_file in data_files:
|
|
# Upload file
|
|
if data_file:
|
|
raw_json = upload_doc(data_file)
|
|
st.sidebar.write(str(data_file.name) + " ✅ ")
|
|
if debug:
|
|
st.subheader("REST API JSON response")
|
|
st.sidebar.write(raw_json)
|
|
|
|
hs_version = ""
|
|
try:
|
|
hs_version = f" <small>(v{haystack_version()})</small>"
|
|
except Exception:
|
|
pass
|
|
|
|
st.sidebar.markdown(
|
|
f"""
|
|
<style>
|
|
a {{
|
|
text-decoration: none;
|
|
}}
|
|
.haystack-footer {{
|
|
text-align: center;
|
|
}}
|
|
.haystack-footer h4 {{
|
|
margin: 0.1rem;
|
|
padding:0;
|
|
}}
|
|
footer {{
|
|
opacity: 0;
|
|
}}
|
|
</style>
|
|
<div class="haystack-footer">
|
|
<hr />
|
|
<h4>Built with <a href="https://www.deepset.ai/haystack">Haystack</a>{hs_version}</h4>
|
|
<p>Get it on <a href="https://github.com/deepset-ai/haystack/">GitHub</a> - Read the <a href="https://haystack.deepset.ai/overview/intro">Docs</a></p>
|
|
<small>Data crawled from <a href="https://en.wikipedia.org/wiki/Category:Lists_of_countries_by_continent">Wikipedia</a> in November 2021.<br />See the <a href="https://creativecommons.org/licenses/by-sa/3.0/">License</a> (CC BY-SA 3.0).</small>
|
|
</div>
|
|
""",
|
|
unsafe_allow_html=True,
|
|
)
|
|
|
|
# Load csv into pandas dataframe
|
|
try:
|
|
df = pd.read_csv(EVAL_LABELS, sep=";")
|
|
except Exception:
|
|
st.error(
|
|
f"The eval file was not found. Please check the demo's [README](https://github.com/deepset-ai/haystack/tree/master/ui/README.md) for more information."
|
|
)
|
|
sys.exit(
|
|
f"The eval file was not found under `{EVAL_LABELS}`. Please check the README (https://github.com/deepset-ai/haystack/tree/master/ui/README.md) for more information."
|
|
)
|
|
|
|
# Search bar
|
|
question = st.text_input("", value=st.session_state.question, max_chars=100, on_change=reset_results)
|
|
col1, col2 = st.columns(2)
|
|
col1.markdown("<style>.stButton button {width:100%;}</style>", unsafe_allow_html=True)
|
|
col2.markdown("<style>.stButton button {width:100%;}</style>", unsafe_allow_html=True)
|
|
|
|
# Run button
|
|
run_pressed = col1.button("Run")
|
|
|
|
# Get next random question from the CSV
|
|
if col2.button("Random question"):
|
|
reset_results()
|
|
new_row = df.sample(1)
|
|
while (
|
|
new_row["Question Text"].values[0] == st.session_state.question
|
|
): # Avoid picking the same question twice (the change is not visible on the UI)
|
|
new_row = df.sample(1)
|
|
st.session_state.question = new_row["Question Text"].values[0]
|
|
st.session_state.answer = new_row["Answer"].values[0]
|
|
st.session_state.random_question_requested = True
|
|
# Re-runs the script setting the random question as the textbox value
|
|
# Unfortunately necessary as the Random Question button is _below_ the textbox
|
|
raise st.script_runner.RerunException(st.script_request_queue.RerunData(None))
|
|
st.session_state.random_question_requested = False
|
|
|
|
run_query = (
|
|
run_pressed or question != st.session_state.question
|
|
) and not st.session_state.random_question_requested
|
|
|
|
# Check the connection
|
|
with st.spinner("⌛️ Haystack is starting..."):
|
|
if not haystack_is_ready():
|
|
st.error("🚫 Connection Error. Is Haystack running?")
|
|
run_query = False
|
|
reset_results()
|
|
|
|
# Get results for query
|
|
if run_query and question:
|
|
reset_results()
|
|
st.session_state.question = question
|
|
|
|
with st.spinner(
|
|
"🧠 Performing neural search on documents... \n "
|
|
"Do you want to optimize speed or accuracy? \n"
|
|
"Check out the docs: https://haystack.deepset.ai/usage/optimization "
|
|
):
|
|
try:
|
|
st.session_state.results, st.session_state.raw_json = query(
|
|
question, top_k_reader=top_k_reader, top_k_retriever=top_k_retriever
|
|
)
|
|
except JSONDecodeError as je:
|
|
st.error("👓 An error occurred reading the results. Is the document store working?")
|
|
return
|
|
except Exception as e:
|
|
logging.exception(e)
|
|
if "The server is busy processing requests" in str(e) or "503" in str(e):
|
|
st.error("🧑🌾 All our workers are busy! Try again later.")
|
|
else:
|
|
st.error("🐞 An error occurred during the request.")
|
|
return
|
|
|
|
if st.session_state.results:
|
|
|
|
# Show the gold answer if we use a question of the given set
|
|
if eval_mode and st.session_state.answer:
|
|
st.write("## Correct answer:")
|
|
st.write(st.session_state.answer)
|
|
|
|
st.write("## Results:")
|
|
|
|
for count, result in enumerate(st.session_state.results):
|
|
if result["answer"]:
|
|
answer, context = result["answer"], result["context"]
|
|
start_idx = context.find(answer)
|
|
end_idx = start_idx + len(answer)
|
|
# Hack due to this bug: https://github.com/streamlit/streamlit/issues/3190
|
|
st.write(
|
|
markdown(context[:start_idx] + str(annotation(answer, "ANSWER", "#8ef")) + context[end_idx:]),
|
|
unsafe_allow_html=True,
|
|
)
|
|
source = ""
|
|
url, title = get_backlink(result)
|
|
if url and title:
|
|
source = f"[{result['document']['meta']['title']}]({result['document']['meta']['url']})"
|
|
else:
|
|
source = f"{result['source']}"
|
|
st.markdown(f"**Relevance:** {result['relevance']} - **Source:** {source}")
|
|
|
|
else:
|
|
st.info(
|
|
"🤔 Haystack is unsure whether any of the documents contain an answer to your question. Try to reformulate it!"
|
|
)
|
|
st.write("**Relevance:** ", result["relevance"])
|
|
|
|
if eval_mode and result["answer"]:
|
|
# Define columns for buttons
|
|
is_correct_answer = None
|
|
is_correct_document = None
|
|
|
|
button_col1, button_col2, button_col3, _ = st.columns([1, 1, 1, 6])
|
|
if button_col1.button("👍", key=f"{result['context']}{count}1", help="Correct answer"):
|
|
is_correct_answer = True
|
|
is_correct_document = True
|
|
|
|
if button_col2.button("👎", key=f"{result['context']}{count}2", help="Wrong answer and wrong passage"):
|
|
is_correct_answer = False
|
|
is_correct_document = False
|
|
|
|
if button_col3.button(
|
|
"👎👍", key=f"{result['context']}{count}3", help="Wrong answer, but correct passage"
|
|
):
|
|
is_correct_answer = False
|
|
is_correct_document = True
|
|
|
|
if is_correct_answer is not None and is_correct_document is not None:
|
|
try:
|
|
send_feedback(
|
|
query=question,
|
|
answer_obj=result["_raw"],
|
|
is_correct_answer=is_correct_answer,
|
|
is_correct_document=is_correct_document,
|
|
document=result["document"],
|
|
)
|
|
st.success("✨ Thanks for your feedback! ✨")
|
|
except Exception as e:
|
|
logging.exception(e)
|
|
st.error("🐞 An error occurred while submitting your feedback!")
|
|
|
|
st.write("___")
|
|
|
|
if debug:
|
|
st.subheader("REST API JSON response")
|
|
st.write(st.session_state.raw_json)
|
|
|
|
|
|
main()
|