Update app.py

app.py

@@ -47,22 +47,6 @@ async def extract_code_blocks(markdown_text):
     
     return code_blocks
 
-async def generate_infographic_details(request: InfographicRequest):
-    description = request.description
-    generated_completion = client.chat.completions.create(
-            model="llama-3.1-70b-versatile",
-            messages=[
-                {"role": "system", "content": SYSTEM_INSTRUCT},
-                {"role": "user", "content": description}
-            ],
-            temperature=0.5,
-            max_tokens=5000,
-            top_p=1,
-            stream=False,
-            stop=None
-        )
-    generated_text = generated_completion.choices[0].message.content
-
 # Route to serve the HTML template
 @app.get("/", response_class=HTMLResponse)
 async def serve_frontend():
@@ -71,15 +55,15 @@ async def serve_frontend():
 # Route to handle infographic generation
 @app.post("/generate")
 async def generate_infographic(request: InfographicRequest):
-    description =await generate_infographic_details(request)
+     description = request.description
     prompt = PROMPT_TEMPLATE.format(description=description)
 
     messages = [{"role": "user", "content": prompt}]
     stream = clientHFInference.chat.completions.create(
         model="Qwen/Qwen2.5-Coder-32B-Instruct",
         messages=messages,
-        temperature=0.4,
-        max_tokens=6000,
+        temperature=0.5,
+        max_tokens=5000,
         top_p=0.7,
         stream=True,
     )
@@ -95,29 +79,3 @@ async def generate_infographic(request: InfographicRequest):
         return JSONResponse(content={"html": code_blocks[0]})
     else:
         return JSONResponse(content={"error": "No generation"},status_code=500)
-    
-    # try:
-    #     messages = [{"role": "user", "content": prompt}]
-    #     stream = client.chat.completions.create(
-    #         model="Qwen/Qwen2.5-Coder-32B-Instruct",
-    #         messages=messages,
-    #         temperature=0.4,
-    #         max_tokens=6000,
-    #         top_p=0.7,
-    #         stream=True,
-    #     )
-
-        
-    #     generated_text = ""
-    #     for chunk in stream:
-    #         generated_text += chunk.choices[0].delta.content
-
-    #     print(generated_text)
-    #     code_blocks= await extract_code_blocks(generated_text)
-    #     if code_blocks:
-    #         return JSONResponse(content={"html": code_blocks[0]})
-    #     else:
-    #         return JSONResponse(content={"error": "No generation"},status_code=500)
-
-    # except Exception as e:
-    #     return JSONResponse(content={"error": str(e)}, status_code=500)