Spaces:
Runtime error
Runtime error
File size: 4,879 Bytes
7a48124 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 |
import dill
import streamlit as st
import os
from haystack.utils import fetch_archive_from_http, clean_wiki_text, convert_files_to_docs
from haystack.schema import Answer
from haystack.document_stores import InMemoryDocumentStore
from haystack.pipelines import ExtractiveQAPipeline
from haystack.nodes import FARMReader, BM25Retriever
import logging
from markdown import markdown
from annotated_text import annotation
from streamlit_lottie import st_lottie
st.set_page_config(page_title="QA-project", page_icon="π")
os.environ['TOKENIZERS_PARALLELISM'] = "false"
DATA_DIR = './dataset'
DOCS_PATH = os.path.join(DATA_DIR, 'all_docs_36838.pkl')
LOTTIE_PATH = 'img/108423-search-for-documents.json'
PROG_TITLE = "QA project Demo"
# 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")
def place_header_center(text, lottie_data):
cgap1, ctitle, cgap2 = st.columns([3, 3, 1])
with cgap1:
st_lottie(lottie_data, height=150)
with ctitle:
st.title(text)
with cgap2:
st.write("")
@st.experimental_memo
def get_lottie(path):
with open(path, 'r', errors='ignore') as f:
lottie_data = json.load(f)
return lottie_data
def load_and_write_data(document_store):
with open(DOCS_PATH, "rb") as f:
docs = dill.load(f)
document_store.write_documents(docs)
# Haystack Components
# @st.cache(allow_output_mutation=True)
# def start_haystack():
document_store = InMemoryDocumentStore(use_bm25=True)
load_and_write_data(document_store)
retriever = BM25Retriever(document_store=document_store)
reader = FARMReader(model_name_or_path="mrm8488/RuPERTa-base-finetuned-squadv1",
use_gpu=False,
num_processes=1)
pipeline = ExtractiveQAPipeline(reader, retriever)
def set_state_if_absent(key, value):
if key not in st.session_state:
st.session_state[key] = value
set_state_if_absent("question", DEFAULT_QUESTION_AT_STARTUP)
set_state_if_absent("answer", DEFAULT_ANSWER_AT_STARTUP)
set_state_if_absent("results", None)
def reset_results(*args):
st.session_state.results = None
# Streamlit App
lottie_data = get_lottie(LOTTIE_PATH)
place_header_center(PROG_TITLE, lottie_data)
st.markdown("""
This QA demo uses a [Haystack Extractive QA Pipeline](https://haystack.deepset.ai/components/ready-made-pipelines#extractiveqapipeline) with
an [InMemoryDocumentStore](https://haystack.deepset.ai/components/document-store) which contains documents about different program modules
Go ahead and ask questions about the program modules functionality!
""", unsafe_allow_html=True)
question = st.text_input("", value=st.session_state.question, max_chars=100, on_change=reset_results)
def ask_question(question):
prediction = pipeline.run(query=question, params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 5}})
results = []
for answer in prediction["answers"]:
answer = answer.to_dict()
if answer["answer"]:
results.append(
{
"context": "..." + answer["context"] + "...",
"answer": answer["answer"],
"relevance": round(answer["score"] * 100, 2),
"offset_start_in_doc": answer["offsets_in_document"][0]["start"],
}
)
else:
results.append(
{
"context": None,
"answer": None,
"relevance": round(answer["score"] * 100, 2),
}
)
return results
if question:
with st.spinner("π°οΈ Performing semantic search on program modules..."):
try:
msg = 'Asked ' + question
logging.info(msg)
st.session_state.results = ask_question(question)
except Exception as e:
logging.exception(e)
if st.session_state.results:
st.write('## Top 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)
st.write(
markdown(context[:start_idx] + str(annotation(body=answer, label="ANSWER", background="#ff700f", color='#ffffff')) + context[end_idx:]),
unsafe_allow_html=True,
)
st.markdown(f"**Relevance:** {result['relevance']}")
else:
st.info(
"π€ Haystack is unsure whether any of the documents contain an answer to your question. Try to reformulate it!"
)
|