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 # url = "https://huggingface.co/TheBloke/Nous-Hermes-13B-GGML/resolve/main/nous-hermes-13b.ggmlv3.q4_0.bin" # response = requests.get(url) # with open("nous-hermes-13b.ggmlv3.q4_0.bin", "wb") as f: # f.write(response.content) 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"]) local_path = ( "./model.bin" ) # # Callbacks support token-wise streaming # callbacks = [StreamingStdOutCallbackHandler()] # Verbose is required to pass to the callback manager llm = LlamaCpp(model_path=("./model.bin")) 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"]) # local_path = "./nous-hermes-13b.ggmlv3.q4_0.bin" # llm = LlamaCpp(model_path=local_path) # 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()