LlamaIndex
Log in

Find answers from the community

Home
Members
Zen
Z
Zen
Offline, last seen last month
Joined December 23, 2024
ZZen
·

Preventing an AI from using chat memory to answer questions

Hi, I have a question on using tool calling. I found that when I add tools the AI first makes the decision properly, calling one or another tools according to the prompt. But, after several questions, it stops calling a tool and answers on its own. My guess is at some point, AI starts using the chat memory which has previously asked questions and answers and gets data from there. Am I right? If so, is there any way to prevent looking the answer in the memory? I thought the passing the empty chat memory could be a solution but unfortunately, I can't do it as it may have the specific information from user that my chatbot should be aware of. The forcing to use a tool doesn't work either because it's based solely when the condition described in the prompt, met. Thanks!
5 comments
L
Z
ZZen
·

How to Prevent Multiple Requests Due to Insufficient Quota When Calling OpenAI API

Hi, when calling a simple code to predict, if there is unsufficient quota on the OpenAI, the code tries to hit the point multiple times what causes 429 error too many requests. How can I prevent these hittings and just get one exception about non-suffitient funds? Thanks
Plain Text
llm = OpenAI(temperature=0, model=model_name, api_key=ai_key, 
                callback_manager=callback_manager)
response = llm.predict(Prompt(prompt))
5 comments
L
Z
ZZen
·

LlamaIndex Update Causes ServiceContext Deprecation

Hi guys,
after updating all the LLamaIndex libs I faced this problem: "ServiceContext is deprecated. Use llama_index.settings.Settings" after checking the documentation, my impression is that I can pass the parameter that I used in the sevicecontext, right into, say, VectorStoreIndex. I didn't find the chunk_size parameter, though. How can I pass it there? Thanks!
```
2 comments
L
Z