Added file uplaod option

.gitattributes

@@ -1,34 +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
+*.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

.ipynb_checkpoints/Test DB-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.streamlit/secrets.toml

@@ -0,0 +1 @@
+pinecone_apikey = "6a76246e-2b5f-46f5-aab8-9cf43d6c94fb"

README.md

@@ -1,13 +1,13 @@
----
-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
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+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
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Test DB.ipynb

@@ -0,0 +1,60 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5736235d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from haystack.document_stores import PineconeDocumentStore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c4925511",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "document_store = PineconeDocumentStore(\n",
+    "        api_key= \"6a76246e-2b5f-46f5-aab8-9cf43d6c94fb\",\n",
+    "        index='qa_demo',\n",
+    "        similarity=\"cosine\",\n",
+    "        embedding_dim=768\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c884286a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "document_store.get"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

app.py

@@ -1,172 +1,241 @@
-import os
-import sys
-import logging
-from pathlib import Path
-from json import JSONDecodeError
-import pandas as pd
-import streamlit as st
-from annotated_text import annotation
-from markdown import markdown
-import json
-from haystack import Document
-import pandas as pd
-from haystack.document_stores import PineconeDocumentStore
-from haystack.nodes import EmbeddingRetriever, FARMReader
-from haystack.pipelines import ExtractiveQAPipeline
-
-# @st.cache
-def create_doc_store():
-    document_store = PineconeDocumentStore(
-        api_key= st.secrets["pinecone_apikey"],
-        index='qa_demo',
-        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)
-
-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")
-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)
-        source = f"[{result.meta['Title']}]({result.meta['link']})"
-        # Hack due to this bug: https://github.com/streamlit/streamlit/issues/3190
-        st.write(
-            markdown(f'**Source:** {source} \n {context[:start_idx] } {str(annotation(answer, "ANSWER", "#8ef"))} {context[end_idx:]} \n '),
-            unsafe_allow_html=True,
-        )
+import os
+import sys
+import logging
+from pathlib import Path
+from json import JSONDecodeError
+import pandas as pd
+import streamlit as st
+from annotated_text import annotation
+from markdown import markdown
+import json
+from haystack import Document
+import pandas as pd
+from haystack.document_stores import PineconeDocumentStore
+from haystack.nodes import EmbeddingRetriever, FARMReader
+from haystack.pipelines import ExtractiveQAPipeline
+import shutil
+import uuid
+from pathlib import Path
+from haystack.pipelines import Pipeline
+from haystack.nodes import TextConverter, PreProcessor, FileTypeClassifier, PDFToTextConverter, DocxToTextConverter
+
+
+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()
+
+
+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='qa_demo',
+        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 = 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)
+
+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"],
+)
+indexing_pipeline_with_classification.add_node(
+    component=document_store, name="DocumentStore", inputs=["Preprocessor"]
+)
+
+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 = []
+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 file_path.open("wb") as buffer:
+            shutil.copyfileobj(data_file.file, buffer)
+        ALL_FILES.append(file_path)
+        st.sidebar.write(str(data_file.name) + " &nbsp;&nbsp; ✅ ")
+        indexing_pipeline_with_classification.run(file_paths=ALL_FILES)
+
+if len(ALL_FILES) > 0:
+    document_store.update_embeddings(retriever, update_existing_embeddings=False)
+        
+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)
+        source = f"[{result.meta['Title']}]({result.meta['link']})"
+        # Hack due to this bug: https://github.com/streamlit/streamlit/issues/3190
+        st.write(
+            markdown(f'**Source:** {source} \n {context[:start_idx] } {str(annotation(answer, "ANSWER", "#8ef"))} {context[end_idx:]} \n '),
+            unsafe_allow_html=True,
+        )

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

@@ -1,7 +1,7 @@
-protobuf==3.19
-streamlit==1.13
-st-annotated-text
-farm-haystack[pinecone]
-pinecone-client
-datasets
+protobuf==3.19
+streamlit==1.13
+st-annotated-text
+farm-haystack[pinecone]
+pinecone-client
+datasets
 tensorboard