Update app.py

app.py

@@ -84,19 +84,27 @@ all_splits = text_splitter.split_documents(docs)
 # -------------------------------
 
 # Create a Chroma vector store using the document splits
-vectorstore = Chroma.from_documents(
-    documents=all_splits, 
-    embedding=OpenAIEmbeddings(), 
-    persist_directory="./chroma_db"
-)
-
+persist_directory = "./chroma_db"
+if os.path.exists(persist_directory) and os.listdir(persist_directory):
+    vectorstore = Chroma(
+        persist_directory=persist_directory,
+        embedding_function=OpenAIEmbeddings()
+    )
+    print("Loaded vector store from persist directory.")
+else:
+    vectorstore = Chroma.from_documents(
+        documents=all_splits, 
+        embedding=OpenAIEmbeddings(), 
+        persist_directory=persist_directory
+    )
+    print("Created new vector store and persisted embeddings.")
 # Create a BM25 retriever from the document splits
 bm25_retriever = BM25Retriever.from_documents(all_splits)
 
 # Combine the retrievers using an ensemble approach
 ensemble_retriever = EnsembleRetriever(
-    retrievers=[vectorstore.as_retriever(search_kwargs={"k": 4}), bm25_retriever],
-    weights=[0.7, 0.3]
+    retrievers=[vectorstore.as_retriever(search_kwargs={"k": 5}), bm25_retriever],
+    weights=[0.8, 0.3]
 )
 retriever = ensemble_retriever
 
@@ -124,21 +132,15 @@ rag_chain = (
     | StrOutputParser()
 )
 system_prompt = (
-    "You are the LA2050 Navigator, an AI-powered chatbot designed to help users explore organizations and community initiatives within the Goldhirsh Foundation’s LA2050 Ideas Hub."
-    "Your role is to provide personalized recommendations, guide users toward supporting these organizations and initiatives, and answer relevant questions about the Goldhirsh Foundation, LA2050, and its projects."
-    "Adhere to these instructions when interacting with the user:"
-    "Start each session by introducing yourself and explaining your purpose before the user inputs any message."
-    "Provide tailored recommendations at a time by default unless the user requests a different number."
-    "Include: the full name of the organization; a brief (1-2 sentence) description; link to the organization personal websites/social"
-    "in the data files; suggestions for how the user can engage, such as donating, volunteering, or learning more."
-    "In your recommendations, prioritize nonprofit organizations awarded by the Goldhirsh Foundation (designated “winner”), as well as organizations with multiple proposal submissions."
-    "Use the data files as your primary source of information when answering questions. If information is unavailable in the files, acknowledge this and guide the user to relevant resources."
-    "Maintain a polite, helpful, respectful, and enthusiastic tone at all times to create a positive user experience."
-    "Politely redirect the user back to relevant topics if they ask unrelated questions, keeping the conversation aligned with your purpose."
-    "Use the following information about the data files to help you:"
-    "The “ideas” are community initiatives submitted by organizations to apply for grants and support from the Goldhirsh Foundation."
-    "There are currently no winners for the 2024 data, although this information can be found on the LA2050 Ideas Hub website. "
-    "Only projects labeled as “winner” in the Project Ranking column should be identified as winning projects."
+    "You are the LA2050 Navigator, an AI-powered chatbot designed to help users explore organizations "
+    "and community initiatives within the Goldhirsh Foundation’s LA2050 Ideas Hub. "
+    "Your role is to provide personalized recommendations, guide users toward supporting these organizations "
+    "and initiatives, and answer relevant questions about the Goldhirsh Foundation, LA2050, and its projects. "
+    "When answering, include the full name of the organization, a brief (1-2 sentence) description, a link to its website or social media, "
+    "and suggestions for engagement such as donating, volunteering, or learning more. "
+    "Prioritize nonprofit organizations awarded by the Goldhirsh Foundation (designated 'winner') and those with multiple proposal submissions. "
+    "Use the data files as your primary source of information. If information is unavailable, acknowledge it and guide the user to relevant resources. "
+    "Maintain a polite, helpful, respectful, and enthusiastic tone at all times. "
     "\n\n{context}"
 )
 prompt = ChatPromptTemplate.from_messages(
@@ -240,17 +242,18 @@ css = """""
 """
 
 # setup gradio interface
-with gr.Blocks(theme=green_theme, js=js_func, css=css) as block:
 
+with gr.Blocks(theme=green_theme, js=js_func, css=css) as block:
     gr.HTML('<div class="chat-header"><h1>LA2050 Navigator</h1></div>')
-
-    chatbot = gr.Chatbot( value=
-                         [{"role": "assistant", "content": "<b>LA2050 Navigator:</b><br> Welcome to the LA2050 ideas hub! How can I help you today?"}],
-                            type="messages",
-                            bubble_full_width=False)
-
+    
+    chatbot = gr.Chatbot(
+        value=[{"role": "assistant", "content": "<b>LA2050 Navigator:</b><br> Welcome to the LA2050 ideas hub! How can I help you today?"}],
+        type="messages",
+        bubble_full_width=False
+    )
+    
     state = gr.State([])
-
+    
     message = gr.MultimodalTextbox(
         interactive=True,
         file_count="multiple",
@@ -258,8 +261,9 @@ with gr.Blocks(theme=green_theme, js=js_func, css=css) as block:
         label="",
         elem_classes="custom-textbox",
         scale=3,
-        show_label=False)
-
+        show_label=False
+    )
+    
     message.submit(
         message_and_history,
         inputs=[message, state],
@@ -267,5 +271,5 @@ with gr.Blocks(theme=green_theme, js=js_func, css=css) as block:
     ).then(
         lambda: "", inputs=[], outputs=message
     )
-
+    
 block.launch(debug=True, share=True)