One of the frequently used templates at Relevance is Summarize meeting transcript. This Tool receives the transcription of a meeting along with information such as meeting agenda and objectives, and produces a summary including all the noted items.
How to use the Tool
Tool inputs and output
The Tool requires four main inputs:
- Meeting context & agenda
- Names of participants
- Data to extract
Provide the main inputs and hit
Run once, you will see the LLM response in a few seconds.
The output is a summary focusing on all the specified points.
Tools and templates can be
tested on individually provided inputs:
set to fetch the data from a dataset and apply the analysis on the whole dataset:
Long text input: An input text component suitable for long text pieces (more than one line), such as answers to a question, reviews, a text to summarize.
This component is to provide the transcription and is of type long tex inputs.
Text input: An input text component suitable for short text pieces, such as name, topic, a question.
This component is to briefly overview the meeting agenda and is of Text input type.
Table: A component for entering structured data as input, for instance, rows of samples, each containing fields such as name, last name and age.
This component is used twice both for providing names and roles of the people in the recording and to specify the objectives, goals and focus points for summarization.
- Enter the names and roles (Use unknown if the data is not available)
- Enter the data you wish to extract along with a brief explanation
There is only 1 LLM component under the Tool steps in this analysis flow.
Large Language Model (LLM)
A large language model component is all set up to provide you access to GPT (and many other LLMs). In the prompt section, you will provide the required information as well as instructions to what is expected to be done.
- Be short and precise with your instruction/request from the LLM
- Note the goals and important instructions closes possible to the end of the prompt
- Specify a data scope using
"""or similar identifiers
- Include formatting instruction when necessary