Update app.py

app.py

@@ -4,10 +4,14 @@
 import os
 import uuid
 import json
+
 import gradio as gr
+
 from openai import OpenAI
+
 from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings
 from langchain_community.vectorstores import Chroma
+
 from huggingface_hub import CommitScheduler
 from pathlib import Path
 
@@ -15,8 +19,8 @@ from pathlib import Path
 anyscale_api_key = userdata.get('anyscale_api_key')  # Ensure to set this environment variable
 
 client = OpenAI(
-    base_url="https://api.endpoints.anyscale.com/v1",
-    api_key=anyscale_api_key
+    #base_url="https://api.endpoints.anyscale.com/v1",
+    api_key=os.environ["anyscale_api_key"]
 )
 
 # Define the embedding model and the vectorstore
@@ -40,6 +44,14 @@ retriever = vectorstore_persisted.as_retriever(
 log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
 log_folder = log_file.parent
 
+scheduler = CommitScheduler(
+    repo_id = "finsight-qna",
+    repo-type = "dataset",
+    folder_path = log_folder,
+    path_in_repo = "data",
+    every = 2
+)
+
 # Define the Q&A system message
 qna_system_message = """
 You are an assistant to a financial technology firm who answers user queries on 10-K reports from various industry players which contain detailed information about financial performance, risk factors, market trends, and strategic initiatives.
@@ -94,14 +106,14 @@ def predict(user_input, company):
     print(prediction)
 
     # Log both the inputs and outputs to a local log file
-    #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