Persist changes from Dev Mode

chain_app.py

@@ -15,7 +15,7 @@ hf_token_llama_3_1 = os.environ.get('HF_TOKEN_FOR_31')
 openai_api_key = os.environ.get('OPENAI_API_KEY')
 groq_api_key = os.environ.get('GROQ_API_KEY')
 cohere_api_key = os.environ.get('COHERE_API_KEY')
-
+fireworks_api_key = os.environ.get('FIREWORKS_API_KEY')
 
 hf_text_client = Client("Artin2009/text-generation", hf_token=hf_token)
 # hf_image_client = Client('Artin2009/image-generation')
@@ -2198,16 +2198,30 @@ async def main(message: cl.Message):
     #     ).send()
         
     elif chat_profile == 'Llama-3.1-405B':        
-        client = Fireworks(api_key="O9D2HQsat357QRQ2wEAC3buShjL8Ea4K7ndDqwkAsAdsDulz")
-        response = client.chat.completions.create(
-        model="accounts/fireworks/models/llama-v3p1-405b-instruct",
-        messages=[{
-           "role": "user",
-           "content": message.content,
-        }],
-        )
+        # client = Fireworks(api_key=f'{fireworks_api_key}')
+        # response = client.chat.completions.create(
+        # model="accounts/fireworks/models/llama-v3p1-405b-instruct",
+        # messages=[{
+        #    "role": "user",
+        #    "content": message.content,
+        # }],
+        # )
+        # await cl.Message(
+        #     content=response.choices[0].message.content,
+        # ).send()
+
+        API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3.1-405B"
+        headers = {"Authorization": "Bearer hf_token_llama_3_1"}
+        def query(payload):
+            response = requests.post(API_URL, headers=headers, json=payload)
+            return response.json()
+        
+        output = query({
+            "inputs": message.content,
+        })
+
         await cl.Message(
-            content=response.choices[0].message.content,
+            content=output
         ).send()