Update app.py

app.py

@@ -1,45 +1,75 @@
-import gradio as gr
-from langchain.llms import LlamaCpp
-from langchain import PromptTemplate, LLMChain
-from langchain.llms import GPT4All
-from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+# import gradio as gr
+# from langchain.llms import LlamaCpp
+# from langchain import PromptTemplate, LLMChain
+# from langchain.llms import GPT4All
+# from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
 
-# import requests
+# # import requests
 
-# url = "https://huggingface.co/TheBloke/Nous-Hermes-13B-GGML/resolve/main/nous-hermes-13b.ggmlv3.q4_0.bin"
+# # url = "https://huggingface.co/TheBloke/Nous-Hermes-13B-GGML/resolve/main/nous-hermes-13b.ggmlv3.q4_0.bin"
 
-# response = requests.get(url)
+# # response = requests.get(url)
 
-# with open("nous-hermes-13b.ggmlv3.q4_0.bin", "wb") as f:
-#     f.write(response.content)
+# # with open("nous-hermes-13b.ggmlv3.q4_0.bin", "wb") as f:
+# #     f.write(response.content)
 
 
-print("DONE")
+# print("DONE")
 
-def func(user):
+# def func(user):
         
-    template = """Question: {question}
+#     template = """
+#     Your name is John and not a assistant but more like a chatbot. Respond precise not more words and act like a human. for example: user: How are you? You: I'm doing good how about you?. user: hello You: Hello how you doing?. Don't say How can I assist you today?.
+#     Question: {question}
     
-    Answer: Let's think step by step."""
+#     Answer: """
     
-    prompt = PromptTemplate(template=template, input_variables=["question"])
+#     prompt = PromptTemplate(template=template, input_variables=["question"])
+    
+#     local_path = (
+#         "./nous-hermes-13b.ggmlv3.q4_0.bin"
+#     )
+
     
-    local_path = (
-        "./nous-hermes-13b.ggmlv3.q4_0.bin"
-    )
+#     # # Callbacks support token-wise streaming
+#     # callbacks = [StreamingStdOutCallbackHandler()]
+    
+#     # Verbose is required to pass to the callback manager
+#     llm = LlamaCpp(model_path="./nous-hermes-13b.ggmlv3.q4_0.bin", n_ctx=2048)
+#     llm_chain = LLMChain(prompt=prompt, llm=llm)
+#     question = user
+#     llm_chain.run(question)
+
+#     return llm_chain.run(question)
+
+# iface = gr.Interface(fn=func, inputs="text", outputs="text")
+# iface.launch()
 
+import gradio as gr
+from langchain.llms import LlamaCpp
+from langchain import PromptTemplate, LLMChain
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+
+print("DONE")
+
+def func(user):
+    template = """
+    Your name is John and not a assistant but more like a chatbot. Respond precise not more words and act like a human. for example: user: How are you? You: I'm doing good how about you?. user: hello You: Hello how you doing?. Don't say How can I assist you today?.
+    Question: {question}
+    
+    Answer: """
+    
+    prompt = PromptTemplate(template=template, input_variables=["question"])
     
-    # # Callbacks support token-wise streaming
-    # callbacks = [StreamingStdOutCallbackHandler()]
+    local_path = "./nous-hermes-13b.ggmlv3.q4_0.bin"
     
-    # Verbose is required to pass to the callback manager
-    llm = LlamaCpp(model_path="./nous-hermes-13b.ggmlv3.q4_0.bin", n_ctx=2048)
-    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    llm = LlamaCpp(model_path=local_path, n_ctx=2048)
+    llm_chain = LLMChain(prompt=prompt, llm=llm, streaming=True)  # Enable streaming mode
     question = user
     llm_chain.run(question)
 
     return llm_chain.run(question)
 
 iface = gr.Interface(fn=func, inputs="text", outputs="text")
-iface.launch()
+iface.launch()