Files
Auto-GPT/scripts
Maiko Bossuyt c986e87135 Edit config Class to manage browse_website command chunk size and summary size
I added two new config parameters:

- browse_chunk_max_length: define the max_length of a chunk being sent to the memory and to FAST_LLM_MODEL for summarizing

- browse_summary_max_token: define the max_token passed to the model use for summary creation. Changing this can help with complex subject, allowing the agent to be more verbose in its attemps to summarize the chunk and the chunks summary.

I've also edited the way the user_agent is handle.
2023-04-12 16:36:27 +02:00
..
2023-04-10 14:25:24 +02:00
2023-04-12 00:11:24 -04:00
2023-04-11 07:53:32 +02:00
2023-04-12 16:32:16 +10:00
2023-04-12 00:11:24 -04:00
2023-04-10 14:25:24 +02:00
2023-04-10 14:25:24 +02:00
2023-04-09 15:42:53 +02:00
2023-04-12 16:23:09 +02:00
2023-04-12 02:26:30 +02:00
2023-04-09 15:39:11 +02:00