update

.gitignore

@@ -1,3 +1,4 @@
 .env
 _app.py
 models/ggml-gpt4all-l13b-snoozy.bin
+myLLM.py

app.py

@@ -1,5 +1,6 @@
 from langchain import PromptTemplate, LLMChain
 from langchain.llms import GPT4All
+from langchain.memory import ConversationMemory
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 import gradio as gr
 from huggingface_hub import hf_hub_download
@@ -16,16 +17,20 @@ template = """Question: {question}
 Answer: Let's think step by step."""
 
 prompt = PromptTemplate(template=template, input_variables=["question"])
+
+# Create a memory module with a maximum capacity of 1000 items
+memory = ConversationMemory(max_capacity=1000)
 # Callbacks support token-wise streaming
 callbacks = [StreamingStdOutCallbackHandler()]
 # Verbose is required to pass to the callback manager
 llm = GPT4All(model=model, callbacks=callbacks, verbose=True)
 
-llm_chain = LLMChain(prompt=prompt, llm=llm)
+llm_chain = LLMChain(prompt=prompt, llm=llm, memory=memory)
 
 # Define the Gradio interface
 def chatbot_interface(input_text):
     response = llm_chain.run(input_text)
+    memory.store(llm_chain.last_input, llm_chain.last_output)
     return response
 
 # Define the Gradio app

myLLM.py

@@ -16,3 +16,4 @@ class AutoModelLanguageModel(LanguageModel):
         output = self.model.generate(prompt, max_length=max_length, pad_token_id=self.tokenizer.pad_token_id)
         response = self.tokenizer.decode(output[0], skip_special_tokens=True)
         return response
+