Update app.py

app.py

@@ -29,7 +29,7 @@ models = [
     # "TinyLlama/TinyLlama-1.1B-Chat-v1.0",     ## high response time
     # "mosaicml/mpt-7b-instruct",     ## 13GB>10GB
     "tiiuae/falcon-7b-instruct",
-    "google/flan-t5-xxl"
+    # "google/flan-t5-xxl" ## high respons time
     # "NousResearch/Yarn-Mistral-7b-128k",  ## 14GB>10GB
     # "Qwen/Qwen2.5-7B-Instruct",     ## 15GB>10GB
 ]
@@ -68,7 +68,11 @@ file_extractor = {
 }
 
 # Embedding model and index initialization (to be populated by uploaded files)
-embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
+# embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
+embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-large-en")
+
+# sentence-transformers/distilbert-base-nli-mean-tokens
+# BAAI/bge-large-en
 # embed_model = HuggingFaceEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
 # Global variable to store documents loaded from user-uploaded files
@@ -102,7 +106,7 @@ def respond(message, history):
         # Initialize the LLM with the selected model
         llm = HuggingFaceInferenceAPI(
             model_name=selected_model_name,
-            token=os.getenv("TOKEN")
+            # token=os.getenv("TOKEN")
         )
 
         # Check selected model