added changes to sync with master

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (search_mlReply)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/search_mlReply.iml" filepath="$PROJECT_DIR$/.idea/search_mlReply.iml" />
+    </modules>
+  </component>
+</project>

.idea/search_mlReply.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

.streamlit/config.toml

@@ -0,0 +1,6 @@
+[theme]
+primaryColor = "#E694FF"
+backgroundColor = "#FFFFFF"
+secondaryBackgroundColor = "#F0F0F0"
+textColor = "#262730"
+font = "sans-serif"

app.py

@@ -7,21 +7,12 @@ from annotated_text import annotation
 from json import JSONDecodeError
 from markdown import markdown
 from utils.config import parser
-from utils.haystack import start_document_store, start_haystack_extractive, start_haystack_rag, query, start_preprocessor_node, start_retriever, start_reader
+from utils.haystack import start_document_store, query, initialize_pipeline, start_preprocessor_node, start_retriever, start_reader
 from utils.ui import reset_results, set_initial_state
-
-# 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_volksbank_QA.csv"))
+import pandas as pd
 
 # Whether the file upload should be enabled or not
 DISABLE_FILE_UPLOAD = bool(os.getenv("DISABLE_FILE_UPLOAD"))
-UPLOAD_DOCUMENTS = []
-
-
 
 # Define a function to handle file uploads
 def upload_files():
@@ -58,23 +49,33 @@ def process_file(data_file, preprocesor, document_store):
 
 try:
     args = parser.parse_args()
-
-    set_initial_state()
-    st.write('# '+args.name)
-    session_state = st.session_state
-
+    #session_state = st.session_state
     preprocesor = start_preprocessor_node()
-    document_store = start_document_store(args.store)
+    document_store = start_document_store(type=args.store)
     retriever = start_retriever(document_store)
     reader = start_reader()
-    if args.task == 'extractive':
-        pipeline = start_haystack_extractive(document_store, retriever, reader)
-    else:
-        pipeline = start_haystack_rag(document_store, retriever)
+    st.set_page_config(
+        page_title="test",
+        layout="centered",
+        page_icon = (":shark:"),
+        menu_items={
+         'Get Help': 'https://www.extremelycoolapp.com/help',
+         'Report a bug': "https://www.extremelycoolapp.com/bug",
+         'About': "# This is a header. This is an *extremely* cool app!"
+     })
+    st.sidebar.image("ml_logo.png", use_column_width=True)
+
+    # Sidebar for Task Selection
+    st.sidebar.header('Options:')
+    task_selection = st.sidebar.radio('Select the task:', ['Extractive', 'Generative'])
+
+    pipeline_rag = initialize_pipeline("rag", document_store, retriever, reader)
+    pipeline_extractive = initialize_pipeline("extractive", document_store, retriever, reader)
+
+    set_initial_state()
 
-    # Sidebar
+    st.write('# ' + args.name)
 
-    #st.sidebar.header("Options")
 
     # File upload block
     if not DISABLE_FILE_UPLOAD:
@@ -97,66 +98,102 @@ try:
                         st.sidebar.write(str(data_file.name) + "    ❌ ")
                         st.sidebar.write("_This file could not be parsed, see the logs for more information._")
 
-
-
+    if "question" not in st.session_state:
+        st.session_state.question = ""
     # Search bar
-    question = st.text_input("Ask a question", value=st.session_state.question, max_chars=100, on_change=reset_results)
-    # question = "what is Pi?"
+    question = st.text_input("", value=st.session_state.question, max_chars=100, on_change=reset_results)
 
     run_pressed = st.button("Run")
-    # run_pressed = True
 
     run_query = (
-        run_pressed or question != st.session_state.question
+        run_pressed or question != st.session_state.question #or task_selection != st.session_state.task
     )
 
     # Get results for query
     if run_query and question:
-        reset_results()
-        st.session_state.question = question
-        with st.spinner("🔎    Running your pipeline"):
-            try:
-                st.session_state.results = query(pipeline, question)
-            except JSONDecodeError as je:
-                st.error(
-                    "👓    An error occurred reading the results. Is the document store working?"
-                )
-            except Exception as e:
-                logging.exception(e)
-                st.error("🐞    An error occurred during the request.")
-            
-                
-
-    if st.session_state.results:
-        results = st.session_state.results
-
-        if args.task == 'extractive':
-            answers = results['answers']
-            for count, answer in enumerate(answers):
-                if answer.answer:
-                    text, context = answer.answer, answer.context
-                    start_idx = context.find(text)
-                    end_idx = start_idx + len(text)
-                    st.write(
-                        f" Answer: {markdown(context[:start_idx] + str(annotation(body=text, label='ANSWER', background='#964448', color='#ffffff')) + context[end_idx:])}",
-                        unsafe_allow_html=True,
+        if task_selection == 'Extractive':
+            reset_results()
+            st.session_state.question = question
+            with st.spinner("🔎    Running your pipeline"):
+                try:
+                    st.session_state.results_extractive = query(pipeline_extractive, question)
+                    st.session_state.task = task_selection
+                except JSONDecodeError as je:
+                    st.error(
+                        "👓    An error occurred reading the results. Is the document store working?"
                     )
-                else:
-                    st.info(
-                        "🤔    Haystack is unsure whether any of the documents contain an answer to your question. Try to reformulate it!"
+                except Exception as e:
+                    logging.exception(e)
+                    st.error("🐞    An error occurred during the request.")
+
+        elif task_selection == 'Generative':
+            reset_results()
+            st.session_state.question = question
+            with st.spinner("🔎    Running your pipeline"):
+                try:
+                    st.session_state.results_generative = query(pipeline_rag, question)
+                    st.session_state.task = task_selection
+                except JSONDecodeError as je:
+                    st.error(
+                        "👓    An error occurred reading the results. Is the document store working?"
                     )
-        elif args.task == 'rag':
-            st.write(f" Answer: {results['results'][0]}")
-        
-                # Extract and display information from the 'documents' list
-        retrieved_documents = results['documents']
-        st.subheader("Retriever Results:")
-        for document in retrieved_documents:
-            st.write(f"Document Name: {document.meta['name']}")
-            st.write(f"Score: {document.score}")
-            st.write(f"Text: {document.content}")
+                except Exception as e:
+                    logging.exception(e)
+                    st.error("🐞    An error occurred during the request.")
+
+    # Display results
+    if (st.session_state.results_extractive or st.session_state.results_generative) and run_query:
+
+        # Handle Extractive Answers
+        if task_selection == 'Extractive':
+            results = st.session_state.results_extractive
+
+            st.subheader("Extracted Answers:")
+
+            if 'answers' in results:
+                answers = results['answers']
+                treshold = 0.2
+                higher_then_treshold = any(ans.score > treshold for ans in answers)
+                if not higher_then_treshold:
+                    st.markdown(f"<span style='color:red'>Please note none of the answers achieved a score higher then {int(treshold) * 100}%. Which probably means that the desired answer is not in the searched documents.</span>", unsafe_allow_html=True)
+                for count, answer in enumerate(answers):
+                    if answer.answer:
+                        text, context = answer.answer, answer.context
+                        start_idx = context.find(text)
+                        end_idx = start_idx + len(text)
+                        score = round(answer.score, 3)
+                        st.markdown(f"**Answer {count + 1}:**")
+                        st.markdown(
+                            context[:start_idx] + str(annotation(body=text, label=f'SCORE {score}', background='#964448', color='#ffffff')) + context[end_idx:],
+                            unsafe_allow_html=True,
+                        )
+                    else:
+                        st.info(
+                            "🤔 &nbsp;&nbsp; Haystack is unsure whether any of the documents contain an answer to your question. Try to reformulate it!"
+                        )
+
+        # Handle Generative Answers
+        elif task_selection == 'Generative':
+            results = st.session_state.results_generative
+            st.subheader("Generated Answer:")
+            if 'results' in results:
+                st.markdown("**Answer:**")
+                st.write(results['results'][0])
+
+        # Handle Retrieved Documents
+        if 'documents' in results:
+            retrieved_documents = results['documents']
+            st.subheader("Retriever Results:")
+
+            data = []
+            for i, document in enumerate(retrieved_documents):
+                # Truncate the content
+                truncated_content = (document.content[:150] + '...') if len(document.content) > 150 else document.content
+                data.append([i + 1, document.meta['name'], truncated_content])
+
+            # Convert data to DataFrame and display using Streamlit
+            df = pd.DataFrame(data, columns=['Ranked Context', 'Document Name', 'Content'])
+            st.table(df)
+
 except SystemExit as e:
-    # This exception will be raised if --help or invalid command line arguments
-    # are used. Currently streamlit prevents the program from exiting normally
-    # so we have to do a hard exit.
-    os._exit(e.code)
+    os._exit(e.code)

utils/config.py

@@ -9,7 +9,7 @@ parser = argparse.ArgumentParser(description='This app lists animals')
 document_store_choices = ('inmemory', 'weaviate', 'milvus', 'opensearch')
 task_choices = ('extractive', 'rag')
 parser.add_argument('--store', choices=document_store_choices, default='inmemory', help='DocumentStore selection (default: %(default)s)')
-parser.add_argument('--task', choices=task_choices, default='rag', help='Task selection (default: %(default)s)')
+#parser.add_argument('--task', choices=task_choices, default='rag', help='Task selection (default: %(default)s)')
 parser.add_argument('--name', default="My Search App")
 
 model_configs = {

utils/haystack.py

@@ -63,6 +63,7 @@ def start_document_store(type: str):
                                             return_embedding=True)
     return document_store
 
+# cached to make index and models load only at start
 @st.cache_resource(show_spinner=False)
 def start_retriever(_document_store: BaseDocumentStore):
     print('initializing retriever')
@@ -104,8 +105,14 @@ def start_haystack_rag(_document_store: BaseDocumentStore, _retriever: Embedding
 
     return pipe
 
-@st.cache_data(show_spinner=True)
+#@st.cache_data(show_spinner=True)
 def query(_pipeline, question):
     params = {}
     results = _pipeline.run(question, params=params)
-    return results
+    return results
+
+def initialize_pipeline(task, document_store, retriever, reader):
+    if task == 'extractive':
+        return start_haystack_extractive(document_store, retriever, reader)
+    elif task == 'rag':
+        return start_haystack_rag(document_store, retriever)

utils/ui.py

@@ -6,7 +6,11 @@ def set_state_if_absent(key, value):
 
 def set_initial_state():
     set_state_if_absent("question", "Ask something here?")
-    set_state_if_absent("results", None)
+    set_state_if_absent("results_extractive", None)
+    set_state_if_absent("results_generative", None)
+    set_state_if_absent("task", None)
 
 def reset_results(*args):
-    st.session_state.results = None
+    st.session_state.results_extractive = None
+    st.session_state.results_generative = None
+    st.session_state.task = None