Upload app.py

app.py

@@ -2,7 +2,6 @@
 
 ## Setup
 # Import the necessary Libraries
-
 import json
 import gradio as gr
 import uuid
@@ -20,8 +19,6 @@ from google.colab import userdata, drive
 from huggingface_hub import CommitScheduler
 
 
-
-
 # Create Client
 load_dotenv()
 
@@ -34,9 +31,7 @@ client = OpenAI(
 
 # Define the embedding model and the vectorstore
 embedding_model = SentenceTransformerEmbeddings(model_name='thenlper/gte-large')
-
 # Load the persisted vectorDB
-
 reportdb = Chroma(
     collection_name=collection_name,
     persist_directory='./report_db1',
@@ -49,7 +44,7 @@ log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
 log_folder = log_file.parent
 
 scheduler = CommitScheduler(
-    repo_id="report-logs",
+    repo_id="---------",
     repo_type="dataset",
     folder_path=log_folder,
     path_in_repo="data",
@@ -74,6 +69,7 @@ If the answer is not found in the context, respond "I don't know".
 
 
 # Define the user message template
+
 qna_user_message_template = """
 ###Context
 Here are some documents that are relevant to the question mentioned below.
@@ -84,7 +80,6 @@ Here are some documents that are relevant to the question mentioned below.
 """
 
 
-
 # Define the predict function that runs when 'Submit' is clicked or when a API request is made
 def predict(user_input,company):
 
@@ -92,51 +87,47 @@ def predict(user_input,company):
     relevant_document_chunks = vectorstore_persisted.similarity_search(user_input, k=5, filter={"source":filter})
 
     # Create context_for_query
-
-relevant_document_chunks = retriever.get_relevant_documents(user_question)
-context_list = [d.page_content for d in relevant_document_chunks]
-context_for_query = ". ".join(context_list)
-
-prompt = [
-    {'role':'system', 'content': qna_system_message},
-    {'role': 'user', 'content': qna_user_message_template.format(
-         context=context_for_query,
-         question=user_question
-        )
-    }
-]
-
-
-
-print(prompt)
-
+    relevant_document_chunks = retriever.get_relevant_documents(user_question)
+    context_list = [d.page_content for d in relevant_document_chunks]
+    context_for_query = ". ".join(context_list)
+
+    prompt = [
+        {'role':'system', 'content': qna_system_message},
+        {'role': 'user', 'content': qna_user_message_template.format(
+             context=context_for_query,
+             question=user_question
+            )
+        }
+    ]
+    print(prompt)
     # Create messages
-response = client.chat.completions.create(
-    model=model_name,
-    messages=prompt,
-    temperature=0
-)
+    response = client.chat.completions.create(
+        model=model_name,
+        messages=prompt,
+        temperature=0
+    )
+
 
     # Get response from the LLM
-answer = response.choices[0].message.content.strip()
-print (answer)
+    answer = response.choices[0].message.content.strip()
+    print (answer)
 
     # While the prediction is made, log both the inputs and outputs to a local log file
     # While writing to the log file, ensure that the commit scheduler is locked to avoid parallel
     # access
 
-with scheduler.lock:
-  with log_file.open("a") as f:
-    f.write(json.dumps(
-             {
-                  'user_input': user_input,
-                  'retrieved_context': context_for_query,
-                  'model_response': prediction
-             }
-          ))
-    f.write("\n")
+    with scheduler.lock:
+        with log_file.open("a") as f:
+            f.write(json.dumps(
+                {
+                    'user_input': user_input,
+                    'retrieved_context': context_for_query,
+                    'model_response': prediction
+                }
+            ))
+            f.write("\n")
 
-  return prediction
+    return prediction
 
 # Set-up the Gradio UI
 # Add text box and radio button to the interface
@@ -148,7 +139,6 @@ company = gr.Radio()
 # Create the interface
 # For the inputs parameter of Interface provide [textbox,company]
 
-demo = gr.Interface(inputs=[textbox,company], fn = predict, output ='text')
 
 demo.queue()
 demo.launch()