1.1

app.py

@@ -22,47 +22,41 @@ with st.sidebar:
     corpus_id = st.text_input("Vectara Corpus ID", value=str(os.getenv("CORPUS_ID", "")))
     openai_api_key = st.text_input("OpenAI API Key", value=os.getenv("OPENAI_API_KEY", ""))
     submit_button = st.button("Submit")
-    
+
 keys_provided = all([customer_id, api_key, corpus_id, openai_api_key])
 
-# Constants
-CUSTOMER_ID = customer_id if customer_id else os.getenv("CUSTOMER_ID")
-API_KEY = api_key if api_key else os.getenv("API_KEY")
-CORPUS_ID = int(corpus_id) if corpus_id else int(os.getenv("CORPUS_ID", 0))  # Assuming CORPUS_ID should be an integer
-OPENAI_API_KEY = openai_api_key if openai_api_key else os.getenv("OPENAI_API_KEY")
+if keys_provided:
+    CUSTOMER_ID = customer_id
+    API_KEY = api_key
+    CORPUS_ID = int(corpus_id)
+    OPENAI_API_KEY = openai_api_key
 
-# Initialize Vectara
-def initialize_vectara():
-    vectara = Vectara(
+    vectara_client = Vectara(
         vectara_customer_id=CUSTOMER_ID,
         vectara_corpus_id=CORPUS_ID,
         vectara_api_key=API_KEY
     )
-    return vectara
-
-vectara_client = initialize_vectara()
 
-# Function to get knowledge content from Vectara
-def get_knowledge_content(vectara, query, threshold=0.5):
-    found_docs = vectara.similarity_search_with_score(
-        query,
-        score_threshold=threshold,
+    # Function to get knowledge content from Vectara
+    def get_knowledge_content(vectara, query, threshold=0.5):
+        found_docs = vectara.similarity_search_with_score(
+            query,
+            score_threshold=threshold,
+        )
+        knowledge_content = ""
+        for number, (score, doc) in enumerate(found_docs):
+            knowledge_content += f"Document {number}: {found_docs[number][0].page_content}\n"
+        return knowledge_content
+
+    # Prompt and response setup
+    prompt = PromptTemplate.from_template(
+        """You are a professional and friendly Legal Consultant and you are helping a client with a legal issue. The client is asking you for advice on a legal issue. Just explain him in detail the answer and nothing else. This is the issue: {issue} 
+        To assist him with his issue, you need to know the following information: {knowledge} 
+        """
     )
-    knowledge_content = ""
-    for number, (score, doc) in enumerate(found_docs):
-        knowledge_content += f"Document {number}: {found_docs[number][0].page_content}\n"
-    return knowledge_content
-
-# Prompt and response setup
-prompt = PromptTemplate.from_template(
-    """You are a professional and friendly Legal Consultant and you are helping a client with a legal issue. The client is asking you for advice on a legal issue. Just explain him in detail the answer and nothing else. This is the issue: {issue} 
-    To assist him with his issue, you need to know the following information: {knowledge} 
-    """
-)
-runnable = prompt | ChatOpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], openai_api_key=OPENAI_API_KEY) | StrOutputParser()
-
-# Main Streamlit App
-if keys_provided:
+    runnable = prompt | ChatOpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], openai_api_key=OPENAI_API_KEY) | StrOutputParser()
+
+    # Main Streamlit App
     st.title("Legal Consultation Chat")
 
     # Initialize chat history
@@ -81,8 +75,6 @@ if keys_provided:
             st.markdown(user_input)
 
         knowledge_content = get_knowledge_content(vectara_client, user_input)
-        print("__________________ Start of knowledge content __________________")
-        print(knowledge_content)
         response = runnable.invoke({"knowledge": knowledge_content, "issue": user_input})
 
         response_words = response.split()