updating the spaces log error

app.py

@@ -13,7 +13,6 @@ from auditqa.process_chunks import load_chunks, getconfig, get_local_qdrant
 from auditqa.retriever import get_context
 from auditqa.reader import nvidia_client, dedicated_endpoint
 from auditqa.utils import make_html_source, parse_output_llm_with_sources, save_logs, get_message_template
-
 from dotenv import load_dotenv
 load_dotenv()
 
@@ -35,7 +34,7 @@ scheduler = CommitScheduler(
      path_in_repo="audit_chatbot",
      token=SPACES_LOG )
 
-#### VECTOR STORE ####
+#####--------------- VECTOR STORE -------------------------------------------------
 # reports contain the already created chunks from Markdown version of pdf reports
 # document processing was done using : https://github.com/axa-group/Parsr
 # We need to create the local vectorstore collection once using load_chunks
@@ -45,7 +44,7 @@ scheduler = CommitScheduler(
 # once the vectore embeddings  are created we will use qdrant client to access these
 vectorstores = get_local_qdrant()
 
-
+#####---------------------CHAT-----------------------------------------------------
 def start_chat(query,history):
     history = history + [(query,None)]
     history = [tuple(x) for x in history]
@@ -59,13 +58,12 @@ async def chat(query,history,sources,reports,subtype,year):
        to yield a tuple of:(messages in gradio format/messages in langchain format, source documents)
     """
 
-    logging.info(f">> NEW QUESTION : {query}")
-    logging.info(f"history:{history}")
-    #print(f"audience:{audience}")
-    logging.info(f"sources:{sources}")
-    logging.info(f"reports:{reports}")
-    logging.info(f"subtype:{subtype}")
-    logging.info(f"year:{year}")
+    print(f">> NEW QUESTION : {query}")
+    print(f"history:{history}")
+    print(f"sources:{sources}")
+    print(f"reports:{reports}")
+    print(f"subtype:{subtype}")
+    print(f"year:{year}")
     docs_html = ""
     output_query = ""
 
@@ -78,9 +76,11 @@ async def chat(query,history,sources,reports,subtype,year):
     context_retrieved_formatted = "||".join(doc.page_content for doc in context_retrieved)
     context_retrieved_lst = [doc.page_content for doc in context_retrieved]
     
-    ##------------------- -------------Prompt--------------------------------------------------
+    ##------------------- -------------Define Prompt-------------------------------------------
     SYSTEM_PROMPT = """
-        You are AuditQ&A, an AI Assistant created by Auditors and Data Scientist. You are given a question and extracted passages of the consolidated/departmental/thematic focus audit reports. Provide a clear and structured answer based on the passages/context provided and the guidelines.
+        You are AuditQ&A, an AI Assistant created by Auditors and Data Scientist. \
+            You are given a question and extracted passages of the consolidated/departmental/thematic focus audit reports.\
+            Provide a clear and structured answer based on the passages/context provided and the guidelines.
         Guidelines:
         - Passeges are provided as comma separated list of strings
         - If the passages have useful facts or numbers, use them in your answer.
@@ -114,9 +114,9 @@ async def chat(query,history,sources,reports,subtype,year):
     if model_config.get('reader','TYPE') == 'NVIDIA':
         chat_model = nvidia_client()
         async def process_stream():
-            nonlocal answer_yet
-            # Without nonlocal, Python would create a new local variable answer_yet inside process_stream(), instead of modifying the one from the outer scope.
-            #nonlocal answer_yet # Use the outer scope's answer_yet variable
+            nonlocal answer_yet # Use the outer scope's answer_yet variable
+            # Without nonlocal, Python would create a new local variable answer_yet inside process_stream(), 
+            # instead of modifying the one from the outer scope.
             # Iterate over the streaming response chunks
             response = chat_model.chat_completion(
                                 model=model_config.get("reader","NVIDIA_MODEL"),
@@ -139,7 +139,8 @@ async def chat(query,history,sources,reports,subtype,year):
     else:
         chat_model = dedicated_endpoint()
         async def process_stream():
-        # Without nonlocal, Python would create a new local variable answer_yet inside process_stream(), instead of modifying the one from the outer scope.
+        # Without nonlocal, Python would create a new local variable answer_yet inside process_stream(), 
+        # instead of modifying the one from the outer scope.
             nonlocal answer_yet # Use the outer scope's answer_yet variable
             # Iterate over the streaming response chunks
             async for chunk in chat_model.astream(messages):
@@ -171,14 +172,14 @@ async def chat(query,history,sources,reports,subtype,year):
                 "answer": history[-1][1],
                 "time": timestamp,
             }
-        save_logs(logs)
+        save_logs(scheduler,JSON_DATASET_PATH,logs)
     except Exception as e:
         logging.error(e)
 
 
 
 
-#### Gradio App ####
+#####-------------------------- Gradio App--------------------------------------####
 
 # Set up Gradio Theme
 theme = gr.themes.Base(

auditqa/process_chunks.py

@@ -16,9 +16,13 @@ device = 'cuda' if cuda.is_available() else 'cpu'
 path_to_data = "./reports/"       
 
 
-##---------------------fucntions -------------------------------------------##
+##---------------------functions -------------------------------------------##
 def getconfig(configfile_path:str):
     """
+    Read the config file
+
+    Params
+    ----------------
     configfile_path: file path of .cfg file
     """
 
@@ -117,9 +121,7 @@ def get_local_qdrant():
         model_kwargs = {'device': device},
         encode_kwargs = {'normalize_embeddings': True},
         model_name=config.get('retriever','MODEL'))
-    #list_ = ['Consolidated','District','Ministry','allreports']
-    #for val in list_:
     client = QdrantClient(path="/data/local_qdrant") 
-    print(client.get_collections())
+    print("Collections in local Qdrant:",client.get_collections())
     qdrant_collections['allreports'] = Qdrant(client=client, collection_name='allreports', embeddings=embeddings, )
     return qdrant_collections

auditqa/reader.py

@@ -13,13 +13,17 @@ HF_token = os.environ["LLAMA_3_1"]
 
 
 def nvidia_client():
+    """ returns the nvidia server client """
     client = InferenceClient(
     base_url=model_config.get('reader','NVIDIA_ENDPOINT'),
     api_key=NVIDIA_SERVER)
+    print("getting nvidia client")
 
     return client
 
 def dedicated_endpoint():
+    """ returns the dedicated server endpoint"""
+
      # Set up the streaming callback handler
     callback = StreamingStdOutCallbackHandler()
 
@@ -36,4 +40,5 @@ def dedicated_endpoint():
     
     # Create a ChatHuggingFace instance with the streaming-enabled endpoint
     chat_model = ChatHuggingFace(llm=llm_qa)
+    print("getting dedicated endpoint wrapped in ChathuggingFace ")
     return chat_model

auditqa/retriever.py

@@ -3,14 +3,13 @@ from auditqa.process_chunks import getconfig
 from langchain.retrievers import ContextualCompressionRetriever
 from langchain.retrievers.document_compressors import CrossEncoderReranker
 from langchain_community.cross_encoders import HuggingFaceCrossEncoder
-import logging
 
 model_config = getconfig("model_params.cfg")
 
 def create_filter(reports:list = [],sources:str =None,
                   subtype:str =None,year:str =None):
     if len(reports) == 0:
-        print("defining filter for:{}:{}:{}".format(sources,subtype,year))
+        print("defining filter for sources:{},subtype:{},year:{}".format(sources,subtype,year))
         filter=rest.Filter(
                 must=[rest.FieldCondition(
                         key="metadata.source",

auditqa/utils.py

@@ -14,7 +14,7 @@ def save_logs(scheduler, JSON_DATASET_PATH, logs) -> None:
         with JSON_DATASET_PATH.open("a") as f:
             json.dump(logs, f)
             f.write("\n")
-    logging.info("logging done")
+    print("logging done")
 
 def get_message_template(type, SYSTEM_PROMPT, USER_PROMPT):
     if type == 'NVIDIA':