Update app.py

app.py

@@ -22,6 +22,7 @@ from langchain.chains.question_answering import load_qa_chain
 
 ### 4. For Gradio App UI
 import gradio as gr
+from huggingface_hub import InferenceClient
 
 fmp_api_key = os.environ['FMP_API_KEY']
 
@@ -40,10 +41,12 @@ chroma_db = Chroma(persist_directory='chromadb_earnings_transcripts_extracted/ch
 # Load the huggingface inference endpoint of an LLM model
 # Name of the LLM model we are using, feel free to try others!
 model = "mistralai/Mistral-7B-Instruct-v0.1"
+hf_client = InferenceClient(model_id=model)
 
 # This is an inference endpoint API from huggingface, the model is not run locally, it is run on huggingface
-hf_llm = HuggingFaceHub(repo_id=model,model_kwargs={'temperature':0.5,"max_new_tokens":300})
+hf_llm = HuggingFaceHub(repo_id=model,model_kwargs={'temperature':0.5,"max_new_tokens":200})
 
+print("### Chroma DB and LLM model loaded successfully...")
 
 def source_question_answer(query:str,vectorstore:Chroma=chroma_db,llm:HuggingFaceHub=hf_llm):
  """