Update app.py

app.py

@@ -16,6 +16,9 @@ from langchain.chains import ConversationalRetrievalChain, LLMChain
 #from langchain.chains import LLMChain
 from langchain_core.prompts import PromptTemplate
 
+# below 2 libraries are for loading remote models
+from transformers import LlamaForCausalLM
+from sentence_transformers import SentenceTransformer
 
 # adding separator
 def add_vertical_space(spaces=1):
@@ -34,7 +37,7 @@ def main():
     TEMP_DIR = "temp"
 
     # embedding model path
-    EMBEDDING_MODEL_PATH = "embeddings/MiniLM-L6-v2"
+    #EMBEDDING_MODEL_PATH = "embeddings/MiniLM-L6-v2"
     
     # creating faiss db direcoty if it doesnot exist already
     if not os.path.exists(TEMP_DIR):
@@ -62,7 +65,10 @@ def main():
         data = loader.load()
 
         # creating embeddings using huggingface
-        embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
+        #embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
+
+        # loading remote embedding model
+        embeddings = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
         
         # creating chunks from CSV file
         #text_splitter = RecursiveCharacterTextSplitter(chunk_size=800, chunk_overlap=50)
@@ -81,17 +87,20 @@ def main():
         docsearch.save_local(DB_FAISS_PATH)
 
         # loading local llama model
-        llm = CTransformers(#model="models/llama-2-7b-chat.ggmlv3.q8_0.bin",
-                            model="TheBloke/Llama-2-7B-Chat-GGML",
-                            model_type="llama",
-                            #callbacks=[StreamingStdOutCallbackHandler()],
-                            config={'max_new_tokens': 1024,
-                                    'temperature': 0.5,
-                                    'context_length' : 4096
-                                    #'repetition_penalty': 1.1
-                                    }
-                            )
-
+        #llm = CTransformers(#model="models/llama-2-7b-chat.ggmlv3.q8_0.bin",
+        #                    model="TheBloke/Llama-2-7B-Chat-GGML",
+        #                    model_type="llama",
+        #                    #callbacks=[StreamingStdOutCallbackHandler()],
+        #                    config={'max_new_tokens': 1024,
+        #                            'temperature': 0.5,
+        #                            'context_length' : 4096
+        #                            #'repetition_penalty': 1.1
+        #                            }
+        #                    )
+
+        # loading remote llama model
+        llm = LlamaForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
+        
         # loading remote zephyr model
         #llm = AutoModelForCausalLM.from_pretrained("TheBloke/zephyr-7B-beta-GGUF", 
         #                                   model_file="zephyr-7b-beta.Q5_K_M.gguf",