Update app.py

app.py

@@ -4,35 +4,40 @@ import os
 import uuid
 import json
 from pathlib import Path
-# Install required libraries if not already installed
-subprocess.check_call([sys.executable, "-m", "pip", "install", "openai"])
-# Install langchain_community if it is not already installed
-subprocess.check_call([sys.executable, "-m", "pip", "install", "langchain_community"])
-# Install sentence-transformers if it is not already installed
-subprocess.check_call([sys.executable, "-m", "pip", "install", "sentence-transformers"])
-# Install sentence-transformers if it is not already installed
-subprocess.check_call([sys.executable, "-m", "pip", "install", "chromadb"])
-subprocess.check_call([sys.executable, "-m", "pip", "install", "python-dotenv"])
 from dotenv import load_dotenv
+
+# Install dependencies if not already installed
+def install_packages():
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "openai"])
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "langchain_community"])
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "sentence-transformers"])
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "chromadb"])
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "huggingface_hub"])
+    subprocess.check_call([sys.executable, "-m", "pip", "install", "python-dotenv"])
+
+install_packages()
+
+# Import installed modules
 from huggingface_hub import login, CommitScheduler
+import openai
 import gradio as gr
 from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings
 from langchain_community.vectorstores import Chroma
-import openai
+
 # Load environment variables from .env file
 load_dotenv()
 
-# Login to Hugging Face using token from environment variables
-hf_token = os.getenv("HF_TOKEN")
-if not hf_token:
-    raise ValueError("Hugging Face token not found in environment variables. Set HF_TOKEN in your .env file.")
-login(hf_token)
-
-# Set OpenAI API key from environment variables
+# Get API tokens from environment variables
+hf_token = os.getenv("HUGGINGFACE_TOKEN")
 openai.api_key = os.getenv("OPENAI_API_KEY")  # Ensure OPENAI_API_KEY is in your .env file
-client = openai
 
-# Set up embeddings and vectorstore
+if hf_token is None:
+    raise ValueError("Hugging Face token is missing. Please check your .env file.")
+
+# Log in to Hugging Face
+login(hf_token)
+
+# Set up embeddings and vector store
 embeddings = SentenceTransformerEmbeddings(model_name="thenlper/gte-large")
 collection_name = 'report-10k-2024'
 
@@ -47,25 +52,11 @@ retriever = vectorstore_persisted.as_retriever(
     search_kwargs={'k': 5}
 )
 
-# Define logging configuration
-log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
-log_folder = log_file.parent
-
-scheduler = CommitScheduler(
-    repo_id="RAGREPORTS-log",
-    repo_type="dataset",
-    folder_path=log_folder,
-    path_in_repo="data",
-    every=2
-)
-
-# Define the Q&A system message
+# Define Q&A system message
 qna_system_message = """
-You are an AI assistant helping Finsights Grey Inc., a financial technology firm, develop a Retrieval-Augmented Generation (RAG) system to automate extraction, summarization, and analysis of 10-K reports.
-Your knowledge base was last updated in August 2023.
-User questions will start with the token: ###Question.
-Answer only based on the provided context.
-If the answer is not found in the context, respond with "I don't know."
+You are an AI assistant for Finsights Grey Inc., helping automate extraction, summarization, and analysis of 10-K reports.
+Your responses should be based solely on the context provided.
+If an answer is not found in the context, respond with "I don't know."
 """
 
 qna_user_message_template = """
@@ -93,29 +84,42 @@ def predict(user_input, company):
 
     # Get response from the LLM
     try:
-        response = client.chat.completions.create(
+        response = openai.ChatCompletion.create(
             model='mistralai/Mixtral-8x7B-Instruct-v0.1',
             messages=prompt,
             temperature=0
         )
         prediction = response.choices[0].message.content
+
     except Exception as e:
         prediction = str(e)
 
     # Log inputs and outputs to a local log file
+    log_file = Path("logs/") / f"data_{uuid.uuid4()}.json"
+    log_folder = log_file.parent
+    scheduler = CommitScheduler(
+        repo_id="RAGREPORTS-log",
+        repo_type="dataset",
+        folder_path=log_folder,
+        path_in_repo="data",
+        every=2
+    )
+
     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(json.dumps(
+                {
+                    'user_input': user_input,
+                    'retrieved_context': context_for_query,
+                    'model_response': prediction
+                }
+            ))
             f.write("\n")
 
     return prediction
 
-# Define the prediction interface function
 def get_predict(question, company):
+    # Map user selection to company name
     company_map = {
         "AWS": "aws",
         "IBM": "IBM",
@@ -126,10 +130,10 @@ def get_predict(question, company):
     selected_company = company_map.get(company)
     if not selected_company:
         return "Invalid company selected"
-    
+
     return predict(question, selected_company)
 
-# Set up the Gradio UI
+# Set-up the Gradio UI
 with gr.Blocks(theme="gradio/seafoam@>=0.0.1,<0.1.0") as demo:
     with gr.Row():
         company = gr.Radio(["AWS", "IBM", "Google", "Meta", "Microsoft"], label="Select a company")
@@ -147,4 +151,9 @@ with gr.Blocks(theme="gradio/seafoam@>=0.0.1,<0.1.0") as demo:
 demo.queue()
 demo.launch()
 
+
+
+
+    
+