ishaan-jaff
|
54514eb11f
|
test(rate limit aware acompletion calls): fix test name
|
2023-10-06 20:52:19 -07:00 |
|
ishaan-jaff
|
498f9aece6
|
test(rate limit aware acompletion calls): testing
|
2023-10-06 20:48:53 -07:00 |
|
ishaan-jaff
|
228d6ea608
|
feat(rate limit aware acompletion calls):
|
2023-10-06 20:48:53 -07:00 |
|
Krrish Dholakia
|
52b0bcb5ec
|
feat(proxy_cli.py): when user calls ollama model, run ollama serve
|
2023-10-06 16:46:52 -07:00 |
|
ishaan-jaff
|
56c87febae
|
chore(stash rate limit manager changes ):
|
2023-10-06 16:22:02 -07:00 |
|
Krrish Dholakia
|
306a38880d
|
feat(ollama.py): exposing ollama config
|
2023-10-06 15:52:58 -07:00 |
|
ishaan-jaff
|
5475d920b8
|
fix(test fix):
|
2023-10-06 15:48:09 -07:00 |
|
ishaan-jaff
|
47521c5a97
|
test commitizen bump
|
2023-10-06 15:41:38 -07:00 |
|
ishaan-jaff
|
4ae8a71aa3
|
bump: version 0.2.5 → 0.3.0
|
2023-10-06 15:40:01 -07:00 |
|
ishaan-jaff
|
6f47a2d6f6
|
test(batch_completion): add tests for batch_completion and rate limit handler
|
2023-10-06 15:37:09 -07:00 |
|
Krrish Dholakia
|
7e34736a38
|
fix(add-custom-success-callback-for-streaming): add custom success callback for streaming
|
2023-10-06 15:02:02 -07:00 |
|
Krrish Dholakia
|
e162a9855b
|
fix(proxy_server.py): make completion call handle "v1" in endpoint url
|
2023-10-06 09:17:02 -07:00 |
|
Krrish Dholakia
|
a977e94a5d
|
style(main.py): adding spacing
|
2023-10-06 06:16:17 -07:00 |
|
Krrish Dholakia
|
06f279807b
|
fix(bedrock.py): adding provider-specific configs
|
2023-10-05 23:49:20 -07:00 |
|
Krrish Dholakia
|
66f6d3e958
|
fix(test_completion.py): fix testing for claude
|
2023-10-05 23:07:26 -07:00 |
|
Krrish Dholakia
|
e9241044b1
|
fix(test_completion.py): fix azure test
|
2023-10-05 22:55:17 -07:00 |
|
Krrish Dholakia
|
e0f1cffa87
|
fix: azure flag check
|
2023-10-05 22:44:41 -07:00 |
|
Krrish Dholakia
|
060a2e40b2
|
fix: fixing mypy linting errors and being backwards compatible for azure=true flag
|
2023-10-05 22:36:32 -07:00 |
|
Krrish Dholakia
|
dd7e397650
|
style(test_completion.py): fix merge conflict
|
2023-10-05 22:09:38 -07:00 |
|
ishaan-jaff
|
4e6e79b20a
|
fix(n param in completion()): fix error thrown when passing n for cohere
|
2023-10-05 19:54:13 -07:00 |
|
ishaan-jaff
|
1897a1ee46
|
fix(llmonitor callback): correctly set user_id
|
2023-10-05 19:36:39 -07:00 |
|
ishaan-jaff
|
8120477be4
|
fix(completion()): add request_timeout as a param, fix claude error when request_timeout set
|
2023-10-05 19:05:28 -07:00 |
|
ishaan-jaff
|
7edaff6198
|
fix ollama tests comments
|
2023-10-05 11:20:34 -07:00 |
|
ishaan-jaff
|
29509a48f8
|
ollama default api_base to http://localhost:11434
|
2023-10-05 11:04:51 -07:00 |
|
Krrish Dholakia
|
ed31860206
|
adding custom prompt templates to ollama
|
2023-10-05 10:48:16 -07:00 |
|
ishaan-jaff
|
e487c33adc
|
remove results.json from tests
|
2023-10-04 16:10:12 -07:00 |
|
ishaan-jaff
|
68698372b0
|
add test batch completions
|
2023-10-04 16:03:58 -07:00 |
|
ishaan-jaff
|
2d4671a7ef
|
add ratelimitmanager
|
2023-10-04 16:03:58 -07:00 |
|
ishaan-jaff
|
e9160a1485
|
fix linting
|
2023-10-04 16:03:58 -07:00 |
|
ishaan-jaff
|
2d281a28b3
|
example output
|
2023-10-04 16:03:58 -07:00 |
|
ishaan-jaff
|
34dc176440
|
make rate limit hadler a class 2
|
2023-10-04 16:03:58 -07:00 |
|
ishaan-jaff
|
68006ff584
|
make RateLimitHandler a class
|
2023-10-04 16:03:58 -07:00 |
|
Krish Dholakia
|
24c12d6b9b
|
Merge pull request #530 from vedant-z/patch-1
Update utils.py
|
2023-10-04 15:42:59 -07:00 |
|
ishaan-jaff
|
a0641ab430
|
add test batch com rate limits
|
2023-10-04 14:46:11 -07:00 |
|
ishaan-jaff
|
defc830e95
|
add batch_completion_rate_limits
|
2023-10-04 14:46:11 -07:00 |
|
ishaan-jaff
|
f6af10b2ca
|
add batch_completion with rate limits to utils
|
2023-10-04 14:46:11 -07:00 |
|
Vedant Borkar
|
c21eae7f79
|
Update utils.py
|
2023-10-05 03:07:50 +05:30 |
|
ishaan-jaff
|
925a6645df
|
pass langfuse host
|
2023-10-04 09:21:46 -07:00 |
|
ishaan-jaff
|
e0373e05ad
|
add langfuse host in callback
|
2023-10-04 09:12:21 -07:00 |
|
Krrish Dholakia
|
95899bf60e
|
add additional param mapping
|
2023-10-03 21:56:08 -07:00 |
|
Krrish Dholakia
|
851cb86daa
|
add support for ai21 input params
|
2023-10-03 21:05:28 -07:00 |
|
ishaan-jaff
|
43c8c88c91
|
test langfuse
|
2023-10-03 21:01:32 -07:00 |
|
ishaan-jaff
|
20f990f652
|
remove print statement
|
2023-10-03 21:01:22 -07:00 |
|
ishaan-jaff
|
1ec15976c5
|
test langfuse added
|
2023-10-03 20:58:40 -07:00 |
|
ishaan-jaff
|
73ad1bf6ed
|
raise error when langfuse not installed
|
2023-10-03 20:58:40 -07:00 |
|
ishaan-jaff
|
ac2d89aee6
|
remove junk print statements
|
2023-10-03 20:58:39 -07:00 |
|
Krrish Dholakia
|
e834c063ff
|
fix n=1 issue with langchain
|
2023-10-03 11:06:59 -07:00 |
|
Krrish Dholakia
|
430e2698a2
|
add param mapping to docs
|
2023-10-03 09:20:58 -07:00 |
|
Krrish Dholakia
|
512769e841
|
support n param for hf
|
2023-10-03 07:10:13 -07:00 |
|
Krrish Dholakia
|
50fc4de45f
|
support cohere top p
|
2023-10-02 21:38:56 -07:00 |
|