Upgrade to GPT-4 and adjust token limits

aimakerspace/openai_utils/chatmodel.py

@@ -6,25 +6,33 @@ load_dotenv()
 
 
 class ChatOpenAI:
-    def __init__(self, model_name: str = "gpt-4o-mini"):
+    def __init__(self, model_name: str = "gpt-4"):
         self.model_name = model_name
         self.openai_api_key = os.getenv("OPENAI_API_KEY")
         if self.openai_api_key is None:
             raise ValueError("OPENAI_API_KEY is not set")
+        self.max_tokens = 8192  # Maximum tokens for response
+        self.max_total_tokens = 16384  # Maximum total tokens (prompt + response)
 
     def run(self, messages, text_only: bool = True, **kwargs):
         if not isinstance(messages, list):
             raise ValueError("messages must be a list")
 
         client = OpenAI()
-        response = client.chat.completions.create(
-            model=self.model_name, messages=messages, **kwargs
-        )
-
-        if text_only:
-            return response.choices[0].message.content
-
-        return response
+        try:
+            response = client.chat.completions.create(
+                model=self.model_name,
+                messages=messages,
+                max_tokens=self.max_tokens,
+                temperature=0.7,  # Add some creativity while maintaining accuracy
+                **kwargs
+            )
+            if text_only:
+                return response.choices[0].message.content
+            return response
+        except Exception as e:
+            print(f"Error in chat completion: {str(e)}")
+            raise
     
     async def astream(self, messages, **kwargs):
         if not isinstance(messages, list):
@@ -32,14 +40,20 @@ class ChatOpenAI:
         
         client = AsyncOpenAI()
 
-        stream = await client.chat.completions.create(
-            model=self.model_name,
-            messages=messages,
-            stream=True,
-            **kwargs
-        )
-
-        async for chunk in stream:
-            content = chunk.choices[0].delta.content
-            if content is not None:
-                yield content
+        try:
+            stream = await client.chat.completions.create(
+                model=self.model_name,
+                messages=messages,
+                max_tokens=self.max_tokens,
+                temperature=0.7,  # Add some creativity while maintaining accuracy
+                stream=True,
+                **kwargs
+            )
+
+            async for chunk in stream:
+                content = chunk.choices[0].delta.content
+                if content is not None:
+                    yield content
+        except Exception as e:
+            print(f"Error in chat completion stream: {str(e)}")
+            raise

chainlit.md

@@ -1,3 +1,14 @@
-# Welcome to Chat with Your Text/PDF File
+# Welcome to Chat with Your Text/PDF File! 📚
 
-With this application, you can chat with an uploaded text/PDFfile that is smaller than 2MB!
+This application allows you to chat with any text or PDF file (up to 2MB) using AI. Here's how to use it:
+
+1. Upload your file (PDF or text)
+2. Wait for processing
+3. Start asking questions about the content
+
+The AI will search through your document and provide relevant answers based on the content.
+
+## Tips
+- For best results, use clear and specific questions
+- The AI works best with well-formatted documents
+- You can ask follow-up questions about the content