Duplicate from Abhilashvj/haystack_QA

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

1.5

@@ -0,0 +1,29 @@
+Requirement already satisfied: tensorboard in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (2.11.0)
+Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (0.4.6)
+Requirement already satisfied: markdown>=2.6.8 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (3.4.1)
+Requirement already satisfied: requests<3,>=2.21.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (2.28.1)
+Requirement already satisfied: absl-py>=0.4 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (1.3.0)
+Requirement already satisfied: setuptools>=41.0.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (65.4.1)
+Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (0.6.1)
+Requirement already satisfied: wheel>=0.26 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (0.37.1)
+Requirement already satisfied: google-auth<3,>=1.6.3 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (2.12.0)
+Requirement already satisfied: protobuf<4,>=3.9.2 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (3.19.4)
+Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (1.8.1)
+Requirement already satisfied: grpcio>=1.24.3 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (1.49.1)
+Requirement already satisfied: numpy>=1.12.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (1.21.6)
+Requirement already satisfied: werkzeug>=1.0.1 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from tensorboard) (2.2.2)
+Requirement already satisfied: six>=1.9.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from google-auth<3,>=1.6.3->tensorboard) (1.16.0)
+Requirement already satisfied: cachetools<6.0,>=2.0.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from google-auth<3,>=1.6.3->tensorboard) (5.2.0)
+Requirement already satisfied: rsa<5,>=3.1.4 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from google-auth<3,>=1.6.3->tensorboard) (4.9)
+Requirement already satisfied: pyasn1-modules>=0.2.1 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from google-auth<3,>=1.6.3->tensorboard) (0.2.8)
+Requirement already satisfied: requests-oauthlib>=0.7.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard) (1.3.1)
+Requirement already satisfied: importlib-metadata>=4.4 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from markdown>=2.6.8->tensorboard) (5.0.0)
+Requirement already satisfied: urllib3<1.27,>=1.21.1 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard) (1.26.12)
+Requirement already satisfied: charset-normalizer<3,>=2 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard) (2.1.1)
+Requirement already satisfied: idna<4,>=2.5 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard) (3.4)
+Requirement already satisfied: certifi>=2017.4.17 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard) (2022.12.7)
+Requirement already satisfied: MarkupSafe>=2.1.1 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from werkzeug>=1.0.1->tensorboard) (2.1.1)
+Requirement already satisfied: zipp>=0.5 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard) (3.11.0)
+Requirement already satisfied: typing-extensions>=3.6.4 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard) (4.4.0)
+Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard) (0.4.8)
+Requirement already satisfied: oauthlib>=3.0.0 in /mnt/e/kaggle2022/conda/envs/pt/lib/python3.7/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard) (3.2.1)

README.md

@@ -0,0 +1,15 @@
+---
+title: Haystack QA
+emoji: 📚
+colorFrom: yellow
+colorTo: green
+sdk: streamlit
+sdk_version: 1.15.2
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: Abhilashvj/haystack_QA
+---
+
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,305 @@
+import json
+import logging
+import os
+import shutil
+import sys
+import uuid
+from json import JSONDecodeError
+from pathlib import Path
+
+import pandas as pd
+import pinecone
+import streamlit as st
+from annotated_text import annotation
+from haystack import Document
+from haystack.document_stores import PineconeDocumentStore
+from haystack.nodes import (
+    DocxToTextConverter,
+    EmbeddingRetriever,
+    FARMReader,
+    FileTypeClassifier,
+    PDFToTextConverter,
+    PreProcessor,
+    TextConverter,
+)
+from haystack.pipelines import ExtractiveQAPipeline, Pipeline
+from markdown import markdown
+from sentence_transformers import SentenceTransformer
+
+index_name = "qa_demo"
+
+
+# connect to pinecone environment
+pinecone.init(
+    api_key=st.secrets["pinecone_apikey"],
+    # environment="us-west1-gcp"
+)
+index_name = "qa-demo"
+
+preprocessor = PreProcessor(
+    clean_empty_lines=True,
+    clean_whitespace=True,
+    clean_header_footer=False,
+    split_by="word",
+    split_length=100,
+    split_respect_sentence_boundary=True
+)
+file_type_classifier = FileTypeClassifier()
+text_converter = TextConverter()
+pdf_converter = PDFToTextConverter()
+docx_converter = DocxToTextConverter()
+
+# check if the abstractive-question-answering index exists
+if index_name not in pinecone.list_indexes():
+    # create the index if it does not exist
+    pinecone.create_index(
+        index_name,
+        dimension=768,
+        metric="cosine"
+    )
+
+# connect to abstractive-question-answering index we created
+index = pinecone.Index(index_name)
+
+FILE_UPLOAD_PATH= "./data/uploads/"
+os.makedirs(FILE_UPLOAD_PATH, exist_ok=True)
+# @st.cache
+def create_doc_store():
+    document_store = PineconeDocumentStore(
+        api_key= st.secrets["pinecone_apikey"],
+        index=index_name,
+        similarity="cosine",
+        embedding_dim=768
+    )
+    return document_store
+
+# @st.cache
+# def create_pipe(document_store):
+    # retriever = EmbeddingRetriever(
+    # document_store=document_store,
+    # embedding_model="sentence-transformers/multi-qa-mpnet-base-dot-v1",
+    # model_format="sentence_transformers",
+    # )
+    # reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False)
+    # pipe = ExtractiveQAPipeline(reader, retriever)
+    # return pipe
+
+def query(pipe, question, top_k_reader, top_k_retriever):
+    res = pipe.run(
+        query=question, params={"Retriever": {"top_k": top_k_retriever}, "Reader": {"top_k": top_k_reader}}
+    )
+    answer_df = []
+    # for r in res['answers']:
+    #     ans_dict = res['answers'][0].meta
+    #     ans_dict["answer"] = r.context
+    #     answer_df.append(ans_dict)
+    # result = pd.DataFrame(answer_df)
+    # result.columns = ["Source","Title","Year","Link","Answer"]
+    # result[["Answer","Link","Source","Title","Year"]] 
+    return res
+
+document_store = create_doc_store()
+# pipe = create_pipe(document_store)
+retriever_model = "sentence-transformers/multi-qa-mpnet-base-dot-v1"
+retriever = EmbeddingRetriever(
+document_store=document_store,
+embedding_model=retriever_model,
+model_format="sentence_transformers",
+)
+# load the retriever model from huggingface model hub
+sentence_encoder = SentenceTransformer(retriever_model)
+
+reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=False)
+pipe = ExtractiveQAPipeline(reader, retriever)
+
+
+indexing_pipeline_with_classification = Pipeline()
+indexing_pipeline_with_classification.add_node(
+    component=file_type_classifier, name="FileTypeClassifier", inputs=["File"]
+)
+indexing_pipeline_with_classification.add_node(
+    component=text_converter, name="TextConverter", inputs=["FileTypeClassifier.output_1"]
+)
+indexing_pipeline_with_classification.add_node(
+    component=pdf_converter, name="PdfConverter", inputs=["FileTypeClassifier.output_2"]
+)
+indexing_pipeline_with_classification.add_node(
+    component=docx_converter, name="DocxConverter", inputs=["FileTypeClassifier.output_4"]
+)
+indexing_pipeline_with_classification.add_node(
+    component=preprocessor,
+    name="Preprocessor",
+    inputs=["TextConverter", "PdfConverter", "DocxConverter"],
+)
+
+def set_state_if_absent(key, value):
+    if key not in st.session_state:
+        st.session_state[key] = value
+
+# 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", "My blog post discusses remote work. Give me statistics.")
+DEFAULT_ANSWER_AT_STARTUP = os.getenv("DEFAULT_ANSWER_AT_STARTUP", "7% more remote workers have been at their current organization for 5 years or fewer")
+
+# 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"))
+
+
+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)
+
+
+# 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 Search Demo")
+st.markdown(
+    """
+This demo takes its data from two sample data csv with statistics on various topics. \n
+Ask any question on this topic and see if Haystack can find the correct answer to your query! \n
+*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")
+st.sidebar.write("## File Upload:")
+data_files = st.sidebar.file_uploader(
+    "upload", type=["pdf", "txt", "docx"], accept_multiple_files=True, label_visibility="hidden"
+)
+ALL_FILES = []
+META_DATA = []
+for data_file in data_files:
+    # Upload file
+    if data_file:
+        file_path = Path(FILE_UPLOAD_PATH) / f"{uuid.uuid4().hex}_{data_file.name}"
+        with open(file_path, "wb") as f:
+            f.write(data_file.getbuffer())
+        ALL_FILES.append(file_path)
+        st.sidebar.write(str(data_file.name) + "    ✅ ")
+        META_DATA.append({"filename":data_file.name})
+        
+
+if len(ALL_FILES) > 0:
+    # document_store.update_embeddings(retriever, update_existing_embeddings=False)
+    docs = indexing_pipeline_with_classification.run(file_paths=ALL_FILES, meta=META_DATA)["documents"]
+    index_name = "qa_demo"
+    # we will use batches of 64
+    batch_size = 64
+    # docs  = docs['documents']
+    with st.spinner(
+            "🧠    Performing indexing of uplaoded documents... \n "
+        ):
+        for i in range(0, len(docs), batch_size):
+            # find end of batch
+            i_end = min(i+batch_size, len(docs))
+            # extract batch
+            batch = [doc.content for doc in docs[i:i_end]]
+            # generate embeddings for batch
+            emb = sentence_encoder.encode(batch).tolist()
+            # get metadata
+            meta = [doc.meta for doc in docs[i:i_end]]
+            # create unique IDs
+            ids = [doc.id for doc in docs[i:i_end]]
+            # add all to upsert list
+            to_upsert = list(zip(ids, emb, meta))
+            # upsert/insert these records to pinecone
+            _ = index.upsert(vectors=to_upsert)
+    
+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,
+)
+# data_files = st.file_uploader(
+#         "upload", type=["csv"], accept_multiple_files=True, label_visibility="hidden"
+#     )
+# for data_file in data_files:
+#     # Upload file
+#     if data_file:
+#         raw_json = upload_doc(data_file)
+
+question = st.text_input(
+        value=st.session_state.question,
+        max_chars=100,
+        on_change=reset_results,
+        label="question",
+        label_visibility="hidden",
+    )
+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")
+if run_pressed:
+
+    run_query = (
+        run_pressed or question != st.session_state.question
+    )
+    # Get results for query
+    if run_query and question:
+        reset_results()
+        st.session_state.question = question
+
+        with st.spinner(
+            "🧠 &nbsp;&nbsp; Performing neural search on documents... \n "
+        ):
+            try:
+                st.session_state.results  = query(
+                    pipe, question, top_k_reader=top_k_reader, top_k_retriever=top_k_retriever
+                )
+            except JSONDecodeError as je:
+                st.error("👓 &nbsp;&nbsp; An error occurred reading the results. Is the document store working?")
+            except Exception as e:
+                logging.exception(e)
+                if "The server is busy processing requests" in str(e) or "503" in str(e):
+                    st.error("🧑‍🌾 &nbsp;&nbsp; All our workers are busy! Try again later.")
+                else:
+                    st.error(f"🐞 &nbsp;&nbsp; An error occurred during the request. {str(e)}")
+
+
+if st.session_state.results:
+
+    st.write("## Results:")
+
+    for count, result in enumerate(st.session_state.results['answers']):
+        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
+        try:
+            source = f"[{result.meta['Title']}]({result.meta['link']})"
+            st.write(
+            markdown(f'**Source:** {source} \n {context[:start_idx] } {str(annotation(answer, "ANSWER", "#8ef"))} {context[end_idx:]} \n '),
+            unsafe_allow_html=True,
+             )
+        except:
+            filename = result.meta.get('filename', "")
+            st.write(
+            markdown(f'From file: {filename} \n {context[:start_idx] } {str(annotation(answer, "ANSWER", "#8ef"))} {context[end_idx:]} \n '),
+            unsafe_allow_html=True,
+            )
+
+        
+        

packages.txt

@@ -0,0 +1,2 @@
+poppler-utils
+xpdf

pinecorn.haystack-pipeline.yml.yml

@@ -0,0 +1,55 @@
+# To allow your IDE to autocomplete and validate your YAML pipelines, name them as <name of your choice>.haystack-pipeline.yml
+
+version: ignore
+
+components:    # define all the building-blocks for Pipeline
+  - name: DocumentStore
+    type: ElasticsearchDocumentStore
+    params:
+      index=: qa_demo
+      similarity: cosine
+      embedding_dim: 768
+  - name: Retriever
+    type: BM25Retriever
+    params:
+      document_store: DocumentStore    # params can reference other components defined in the YAML
+      top_k: 5
+  - name: Reader       # custom-name for the component; helpful for visualization & debugging
+    type: FARMReader    # Haystack Class name for the component
+    params:
+      model_name_or_path: deepset/roberta-base-squad2
+      context_window_size: 500
+      return_no_answer: true
+  - name: TextFileConverter
+    type: TextConverter
+  - name: PDFFileConverter
+    type: PDFToTextConverter
+  - name: Preprocessor
+    type: PreProcessor
+    params:
+      split_by: word
+      split_length: 1000
+  - name: FileTypeClassifier
+    type: FileTypeClassifier
+
+pipelines:
+  - name: query    # a sample extractive-qa Pipeline
+    nodes:
+      - name: Retriever
+        inputs: [Query]
+      - name: Reader
+        inputs: [Retriever]
+  - name: indexing
+    nodes:
+      - name: FileTypeClassifier
+        inputs: [File]
+      - name: TextFileConverter
+        inputs: [FileTypeClassifier.output_1]
+      - name: PDFFileConverter
+        inputs: [FileTypeClassifier.output_2]
+      - name: Preprocessor
+        inputs: [PDFFileConverter, TextFileConverter]
+      - name: Retriever
+        inputs: [Preprocessor]
+      - name: DocumentStore
+        inputs: [Retriever]

requirements.txt

@@ -0,0 +1,8 @@
+protobuf==3.19
+streamlit==1.13
+st-annotated-text
+farm-haystack[pinecone]
+farm-haystack[ocr]
+pinecone-client
+datasets
+tensorboard

search.py

@@ -0,0 +1,60 @@
+
+
+import pinecone
+index_name = "abstractive-question-answering"
+
+# check if the abstractive-question-answering index exists
+if index_name not in pinecone.list_indexes():
+    # create the index if it does not exist
+    pinecone.create_index(
+        index_name,
+        dimension=768,
+        metric="cosine"
+    )
+
+# connect to abstractive-question-answering index we created
+index = pinecone.Index(index_name)
+
+# we will use batches of 64
+batch_size = 64
+
+for i in tqdm(range(0, len(df), batch_size)):
+    # find end of batch
+    i_end = min(i+batch_size, len(df))
+    # extract batch
+    batch = df.iloc[i:i_end]
+    # generate embeddings for batch
+    emb = retriever.encode(batch["passage_text"].tolist()).tolist()
+    # get metadata
+    meta = batch.to_dict(orient="records")
+    # create unique IDs
+    ids = [f"{idx}" for idx in range(i, i_end)]
+    # add all to upsert list
+    to_upsert = list(zip(ids, emb, meta))
+    # upsert/insert these records to pinecone
+    _ = index.upsert(vectors=to_upsert)
+
+# check that we have all vectors in index
+index.describe_index_stats()
+
+# from transformers import BartTokenizer, BartForConditionalGeneration
+
+# # load bart tokenizer and model from huggingface
+# tokenizer = BartTokenizer.from_pretrained('vblagoje/bart_lfqa')
+# generator = BartForConditionalGeneration.from_pretrained('vblagoje/bart_lfqa')
+
+# def query_pinecone(query, top_k):
+#     # generate embeddings for the query
+#     xq = retriever.encode([query]).tolist()
+#     # search pinecone index for context passage with the answer
+#     xc = index.query(xq, top_k=top_k, include_metadata=True)
+#     return xc
+
+# def format_query(query, context):
+#     # extract passage_text from Pinecone search result and add the  tag
+#     context = [f" {m['metadata']['passage_text']}" for m in context]
+#     # concatinate all context passages
+#     context = " ".join(context)
+#     # contcatinate the query and context passages
+#     query = f"question: {query} context: {context}"
+#     return query