James Collins
|
91aa40e0df
|
Remove another global memory access
|
2023-04-23 16:59:49 -07:00 |
|
bszollosinagy
|
fa91bc154c
|
Fix model context overflow issue (#2542)
Co-authored-by: batyu <batyu@localhost>
|
2023-04-19 23:28:57 +02:00 |
|
itaihochman
|
e34ede79b9
|
Add an option to set the chunk size using the
configoration - BROWSE_CHUNK_MAX_LENGTH=4000
This way, we can avoid errors of exceeding chunk size when using gpt-3.5
|
2023-04-18 08:56:00 +03:00 |
|
Merwane Hamadi
|
cf9a94a8b6
|
isort implemented
|
2023-04-17 13:42:01 -07:00 |
|
Tom Kaitchuck
|
6b64158356
|
Unbound summary size
Signed-off-by: Tom Kaitchuck <Tom.Kaitchuck@gmail.com>
|
2023-04-17 17:08:21 +01:00 |
|
Richard Beales
|
fdac81e908
|
Merge pull request #1489 from hdkiller/remove-please-from-prompts
Remove please from prompts
|
2023-04-15 18:45:05 +01:00 |
|
HDKiller
|
885d81b354
|
remove "please" from prompt in text.py
|
2023-04-15 16:55:32 +00:00 |
|
youkaichao
|
a51b37f01c
|
fix dict type annotation
|
2023-04-15 22:10:22 +08:00 |
|
BillSchumacher
|
1073954fb7
|
Reorg (#1537)
* Pi's message.
* Fix most everything.
* Blacked
* Add Typing, Docstrings everywhere, organize the code a bit.
* Black
* fix import
* Update message, dedupe.
* Increase backoff time.
* bump up retries
|
2023-04-15 13:56:23 +01:00 |
|