Update app.py

app.py

@@ -1,69 +1,112 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from openai import OpenAI
+import os
+import glob
+from pypdf import PdfReader
 
+# Initialize client using Hugging Face routing
+client = OpenAI(
+    base_url="https://router.huggingface.co/v1",
+    api_key=os.environ.get("HF_TOKEN"),
+)
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+# --- Document Context Logic ---
+DOCS_DIR = "docs" # Folder for your JMeter cheat sheets, project specs, etc.
 
-    messages = [{"role": "system", "content": system_message}]
+def load_pdf_context():
+    """Reads all PDFs in the DOCS_DIR once at startup and extracts text."""
+    context = ""
+    if not os.path.exists(DOCS_DIR):
+        os.makedirs(DOCS_DIR)
+        print(f"Created '{DOCS_DIR}' directory. Upload your PDFs here.")
+        return context
+        
+    pdf_files = glob.glob(os.path.join(DOCS_DIR, "*.pdf"))
+    if not pdf_files:
+        print("No PDFs found in the docs folder.")
+        return context
+        
+    print(f"Loading {len(pdf_files)} PDF(s) into context...")
+    for file_path in pdf_files:
+        try:
+            reader = PdfReader(file_path)
+            context += f"\n--- Start Document: {os.path.basename(file_path)} ---\n"
+            for page in reader.pages:
+                text = page.extract_text()
+                if text:
+                    context += text + "\n"
+            context += f"--- End Document: {os.path.basename(file_path)} ---\n\n"
+        except Exception as e:
+            print(f"Error loading {file_path}: {e}")
+            
+    return context
 
-    messages.extend(history)
+DOCUMENT_CONTEXT = load_pdf_context()
+# -----------------------------------
 
-    messages.append({"role": "user", "content": message})
+def respond(message, history):
+    # System Message tailored for an experienced Dev learning JMeter
+    system_content = (
+        "You are a highly experienced Performance Engineer and Apache JMeter expert. "
+        "The user you are helping is an experienced software developer who is new to JMeter and stress testing. "
+        "Skip basic programming concepts and focus strictly on JMeter architecture (Test Plans, Thread Groups, Samplers, Listeners, Timers), "
+        "performance testing theory (Load vs. Stress vs. Spike testing), and best practices (e.g., using JSR223 Samplers with Groovy instead of BeanShell, running in CLI/non-GUI mode). "
+        "Be concise, technical, and highly practical. Provide code snippets or XML structures where helpful.\n\n"
+        "Here is the project-specific context and documentation you should use to answer questions:\n"
+        f"{DOCUMENT_CONTEXT}"
+    )
+    
+    messages = [{"role": "system", "content": system_content}]
+    
+    # Add conversation history
+    for val in history:
+        if val['role'] == 'user':
+            messages.append({"role": "user", "content": val['content']})
+        else:
+            messages.append({"role": "assistant", "content": val['content']})
 
-    response = ""
+    # Process the current message
+    user_content = []
+    if message["text"]:
+        user_content.append({"type": "text", "text": message["text"]})
+    
+    # Image/File handling placeholder
+    for file in message["files"]:
+        pass 
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+    messages.append({"role": "user", "content": user_content})
 
-        response += token
-        yield response
+    response = ""
+    
+    try:
+        stream = client.chat.completions.create(
+            # You can keep this model or switch to another available on HF-Pro
+            model="moonshotai/Kimi-K2.5:together", 
+            messages=messages,
+            stream=True
+        )
 
+        for chunk in stream:
+            if hasattr(chunk, 'choices') and len(chunk.choices) > 0:
+                token = chunk.choices[0].delta.content
+                if token:
+                    response += token
+                    yield response
+    except Exception as e:
+        yield f"Error encountered: {str(e)} - Please verify the model endpoint or your API token."
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
+# Interface Setup
+demo = gr.ChatInterface(
     respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+    multimodal=True, 
+    title="Apache JMeter Performance Expert ⚙️",
+    description="Your technical guide for building robust JMeter test plans, analyzing performance metrics, and executing effective stress tests. Backed by your project documentation.",
+    examples=[
+        {"text": "What is the difference between a Load Test and a Stress Test?"},
+        {"text": "How do I extract a dynamic token from a JSON response to use in my next request?"},
+        {"text": "Why should I run my tests in non-GUI mode, and what is the command for it?"}
+    ]
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()