Update app.py

app.py

@@ -2,21 +2,44 @@
 import gradio as gr
 import json
 import re
+import os
 from datetime import datetime
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+from huggingface_hub import login
+
+# First, login with the Hugging Face token from secrets
+try:
+    hf_token = os.environ.get('HUGGINGFACE_TOKEN')
+    if hf_token:
+        login(token=hf_token)
+    else:
+        raise ValueError("HUGGINGFACE_TOKEN not found in environment variables")
+except Exception as e:
+    print(f"Error during Hugging Face login: {str(e)}")
+    raise
 
 class TranscriptAnalyzer:
     def __init__(self):
-        # Initialize the model and tokenizer
-        self.model_name = "mistralai/Mistral-7B-Instruct-v0.2"
-        self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
-        self.model = AutoModelForCausalLM.from_pretrained(
-            self.model_name,
-            torch_dtype=torch.float16,
-            device_map="auto"
-        )
-        
+        try:
+            # Initialize the model and tokenizer with auth token
+            self.model_name = "mistralai/Mistral-7B-Instruct-v0.2"
+            self.tokenizer = AutoTokenizer.from_pretrained(
+                self.model_name,
+                token=hf_token,
+                trust_remote_code=True
+            )
+            self.model = AutoModelForCausalLM.from_pretrained(
+                self.model_name,
+                token=hf_token,
+                torch_dtype=torch.float16,
+                device_map="auto",
+                trust_remote_code=True
+            )
+        except Exception as e:
+            print(f"Error initializing model: {str(e)}")
+            raise
+
     def extract_dates(self, text: str):
         date_patterns = [
             r'\d{1,2}[-/]\d{1,2}[-/]\d{2,4}',
@@ -83,34 +106,40 @@ FOLLOW UP:
 - Pending items [/INST]</s>"""
 
     def analyze_transcript(self, transcript: str):
-        # Generate prompt
-        prompt = self.generate_prompt(transcript)
-        
-        # Tokenize input
-        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)
-        
-        # Generate response
-        with torch.no_grad():
-            outputs = self.model.generate(
-                **inputs,
-                max_new_tokens=1000,
-                temperature=0.1,
-                do_sample=True,
-                pad_token_id=self.tokenizer.eos_token_id
-            )
-        
-        # Decode response
-        response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
-        
-        # Extract the assistant's response (after the prompt)
-        response = response.split("[/INST]")[-1].strip()
-        
-        return response
+        try:
+            # Generate prompt
+            prompt = self.generate_prompt(transcript)
+            
+            # Tokenize input
+            inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)
+            
+            # Generate response
+            with torch.no_grad():
+                outputs = self.model.generate(
+                    **inputs,
+                    max_new_tokens=1000,
+                    temperature=0.1,
+                    do_sample=True,
+                    pad_token_id=self.tokenizer.eos_token_id
+                )
+            
+            # Decode response
+            response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+            
+            # Extract the assistant's response (after the prompt)
+            response = response.split("[/INST]")[-1].strip()
+            
+            return response
+        except Exception as e:
+            return f"Error analyzing transcript: {str(e)}"
 
 def process_transcript(transcript: str):
-    analyzer = TranscriptAnalyzer()
-    analysis = analyzer.analyze_transcript(transcript)
-    return analysis
+    try:
+        analyzer = TranscriptAnalyzer()
+        analysis = analyzer.analyze_transcript(transcript)
+        return analysis
+    except Exception as e:
+        return f"Error processing transcript: {str(e)}"
 
 # Create Gradio interface
 iface = gr.Interface(
@@ -135,4 +164,5 @@ iface = gr.Interface(
 )
 
 # Launch the app
-iface.launch()
+if __name__ == "__main__":
+    iface.launch()