Update app.py

app.py

@@ -15,14 +15,27 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 #from transformers import pipeline
 # Load model directly
 #from transformers import AutoModelForCausalLM
-from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
-
+#from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
+from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
+from llama_index.llms.huggingface import HuggingFaceInferenceAPI
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 
 
 
 #access_token = os.getenv("HUGGINGFACE_API_KEY")
 
-
+# Configure the Llama index settings
+Settings.llm = HuggingFaceInferenceAPI(
+    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
+    tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
+    context_window=3900,
+    token=os.getenv("HUGGINGFACE_API_KEY"),
+    # max_new_tokens=1000,
+    generate_kwargs={"temperature": 0.1},
+)
+Settings.embed_model = HuggingFaceEmbedding(
+    model_name="BAAI/bge-small-en-v1.5"
+)
 
 #st.set_page_config(page_title="Document Genie", layout="wide")
 
@@ -97,10 +110,10 @@ def get_conversational_chain(retriever):
     #llm = AutoModelForCausalLM.from_pretrained("google/gemma-1.1-2b-it")
     #llm = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True, token=access_token)
     #llm = pipeline("text-generation", model="google/gemma-1.1-2b-it")
-    llm = HuggingFacePipeline.from_model_id(
-    model_id="gpt2",
-    task="text-generation",
-    pipeline_kwargs={"max_new_tokens": 10})
+    #llm = HuggingFacePipeline.from_model_id(
+    #model_id="gpt2",
+    #task="text-generation",
+    #pipeline_kwargs={"max_new_tokens": 10})
 
     pt = ChatPromptTemplate.from_template(prompt_template)
     # Retrieve and generate using the relevant snippets of the blog.