Update app.py

app.py

@@ -79,6 +79,21 @@ async def chat(query,history,sources,reports):
       task="text-generation",
       huggingfacehub_api_token=HF_token,
       model_kwargs={})
+
+# trying llm new-prompt adapted for llama-3
+# https://stackoverflow.com/questions/78429932/langchain-ollama-and-llama-3-prompt-and-response
+# https://api.python.langchain.com/en/latest/llms/langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.html#langchain_community.llms.huggingface_endpoint.HuggingFaceEndpoint.model_kwargs
+# https://huggingface.co/blog/llama3#how-to-prompt-llama-3
+
+    llm_qa = HuggingFaceEndpoint(
+      endpoint_url= "https://mnczdhmrf7lkfd9d.eu-west-1.aws.endpoints.huggingface.cloud",
+      task="text-generation",
+      huggingfacehub_api_token=HF_token,
+      truncate = 1500,
+      stop=["<|eot_id|>"],
+      streaming-True,
+      model_kwargs={})
+
     
 # create rag chain
     chain = prompt | llm_qa | StrOutputParser()