Find answers from the community

Updated 2 months ago

hi all i have collected my meeting

hi all, i have collected my meeting scripts from the recording. Can anyone show me the simple code to use llamaindex, go through all the chunks/nodes, and provide some summary information of meeting, like key topics were discussed, key decision were made, and actions should be taken, ownership and due date , etc ?

8 comments

EEmanuel Ferreira

https://gpt-index.readthedocs.io/en/latest/getting_started/starter_example.html

aautratec

Was vector index effective for meeting minutes development? Or should use tree index or list index?

LLogan M

I would just use a list index with response_mode="tree_summarize"

Although you might need to increase the token output if you expect that response to be longer than 256 tokens

aautratec

Any example code can be shared? Do u mean I still ues vector index, but add response_mode in the query_engine ?

LLogan M

No vector index, list index is fine

LLogan M

I can write an example in a sec

LLogan M

Plain Text

from llama_index.llms import OpenAI

llm = OpenAI(model="gpt-3.5-turbo-0613", temperature=0.0, max_tokens=512)
service_context = ServiceContext.from_defaults(llm=llm)

index = ListIndex.from_documents(documents, service_context=service_context)
query_engine = index.as_query_engine(response_mode="tree_summarize")
response = query_engine.query("Summarize the meeting notes. Be sure to include key topics, decisions, and action items.")

aautratec

it looks working well for me to prepare the meeting minutes.

Add a reply