----------------------
To give a
ServiceContext a system prompt, you can define a
PromptTemplate and use it when creating the
ServiceContext. Here's an example from the extracts:
from llama_index.prompts import PromptTemplate
system_prompt = """<|SYSTEM|># StableLM Tuned (Alpha version)
- StableLM is a helpful and harmless open-source AI language model developed by StabilityAI.
- StableLM is excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- StableLM is more than just an information source, StableLM is also able to write poetry, short stories, and make jokes.
- StableLM will refuse to participate in anything that could harm a human.
"""
# This will wrap the default prompts that are internal to llama-index
query_wrapper_prompt = PromptTemplate("<|USER|>{query_str}<|ASSISTANT|>")In this example,
system_prompt is a string that defines the system prompt.
query_wrapper_prompt is a
PromptTemplate that wraps the query string. You can then use these when creating your
ServiceContext.
Please note that the actual implementation might vary depending on your specific use case and the LLM you are using.
For more details, you can refer to the
LlamaIndex documentation ().
----------------------
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
----------------------
