Update app.py

app.py

@@ -1,13 +1,13 @@
-import gradio as gr
+# import gradio as gr
 
-from langchain_community.llms import LlamaCpp
-from langchain.prompts import PromptTemplate
-from langchain.chains import LLMChain
-from langchain_core.callbacks import StreamingStdOutCallbackHandler
-from langchain.retrievers import TFIDFRetriever
-from langchain.chains import RetrievalQA
-from langchain.memory import ConversationBufferMemory
-from langchain_community.chat_models import ChatLlamaCpp
+# from langchain_community.llms import LlamaCpp
+# from langchain.prompts import PromptTemplate
+# from langchain.chains import LLMChain
+# from langchain_core.callbacks import StreamingStdOutCallbackHandler
+# from langchain.retrievers import TFIDFRetriever
+# from langchain.chains import RetrievalQA
+# from langchain.memory import ConversationBufferMemory
+# from langchain_community.chat_models import ChatLlamaCpp
 
 
 # callbacks = [StreamingStdOutCallbackHandler()]
@@ -30,73 +30,73 @@ from langchain_community.chat_models import ChatLlamaCpp
 
 
 
-def greet(question, model_type):
-    print(f"question is {question}")
-    out_gen = "testsetestestetsetsets"
-    return out_gen
+# def greet(question, model_type):
+#     print(f"question is {question}")
+#     out_gen = "testsetestestetsetsets"
+#     return out_gen
 
-demo = gr.Interface(fn=greet, inputs=["text", gr.Dropdown(
-            ["With memory", "Without memory"], label="Memory status", info="With using memory, the output will be slow but strong"
-        ),], outputs="text")
-demo.launch(debug=True, share=True)
+# demo = gr.Interface(fn=greet, inputs=["text", gr.Dropdown(
+#             ["With memory", "Without memory"], label="Memory status", info="With using memory, the output will be slow but strong"
+#         ),], outputs="text")
+# demo.launch(debug=True, share=True)
 
 
-# import gradio as gr
+import gradio as gr
 
-# from langchain_community.llms import LlamaCpp
-# from langchain.prompts import PromptTemplate
-# from langchain.chains import LLMChain
-# from langchain_core.callbacks import StreamingStdOutCallbackHandler
-# from langchain.retrievers import TFIDFRetriever
-# from langchain.chains import RetrievalQA
-# from langchain.memory import ConversationBufferMemory
-# from langchain_community.chat_models import ChatLlamaCpp
+from langchain_community.llms import LlamaCpp
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
+from langchain_core.callbacks import StreamingStdOutCallbackHandler
+from langchain.retrievers import TFIDFRetriever
+from langchain.chains import RetrievalQA
+from langchain.memory import ConversationBufferMemory
+from langchain_community.chat_models import ChatLlamaCpp
 
-# callbacks = [StreamingStdOutCallbackHandler()]
-# print("creating ll started")
-# M_NAME = "finbro-v0.1.0-llama-3-8B-instruct-1m.gguf"
-# llm = ChatLlamaCpp(
-#     model_path=M_NAME,
-#     n_batch=8,
-#     temperature=0.85,
-#     max_tokens=256,
-#     top_p=0.95,
-#     top_k = 10,
-#     callback_manager=callbacks,
-#     n_ctx=2048,
-#     verbose=True,  # Verbose is required to pass to the callback manager
-# )
-# # print("creating ll ended")
+callbacks = [StreamingStdOutCallbackHandler()]
+print("creating ll started")
+M_NAME = "finbro-v0.1.0-llama-3-8B-instruct-1m.gguf"
+llm = ChatLlamaCpp(
+    model_path=M_NAME,
+    n_batch=8,
+    temperature=0.85,
+    max_tokens=256,
+    top_p=0.95,
+    top_k = 10,
+    callback_manager=callbacks,
+    n_ctx=2048,
+    verbose=True,  # Verbose is required to pass to the callback manager
+)
+# print("creating ll ended")
 
 
 
 
 
 
-# def greet(question, model_type):
-#     print("prompt started ")
-#     print(f"question is {question}")
-#     template = """You are the Finiantial expert:
+def greet(question, model_type):
+    print("prompt started ")
+    print(f"question is {question}")
+    template = """You are the Finiantial expert:
     
-#     ### Instruction:
-#     {question}
+    ### Instruction:
+    {question}
     
-#     ### Input:
+    ### Input:
     
     
-#     ### Response:
-#     """
-#     print("test1")
-#     prompt = PromptTemplate(template=template, input_variables=["question"])
-#     print("test2")
-#     llm_chain_model = LLMChain(prompt=prompt, llm=llm)
-#     print("test3")
-#     out_gen = llm_chain_model.run(question)  
-#     print("test4")
-#     print(f"out is: {out_gen}")
-#     return out_gen
+    ### Response:
+    """
+    print("test1")
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+    print("test2")
+    llm_chain_model = LLMChain(prompt=prompt, llm=llm)
+    print("test3")
+    out_gen = llm_chain_model.run(question)  
+    print("test4")
+    print(f"out is: {out_gen}")
+    return out_gen
 
-# demo = gr.Interface(fn=greet, inputs=["text", gr.Dropdown(
-#             ["Without memory", "With memory"], label="Memory status", info="With using memory, the output will be slow but strong"
-#         ),], outputs="text")
-# demo.launch(debug=True, share=True)
+demo = gr.Interface(fn=greet, inputs=["text", gr.Dropdown(
+            ["Without memory", "With memory"], label="Memory status", info="With using memory, the output will be slow but strong"
+        ),], outputs="text")
+demo.launch(debug=True, share=True)