ishaan-jaff
|
bcf22725a6
|
(ci/cd) run cloudflare test 3 retries
|
2024-01-05 11:55:12 +05:30 |
|
ishaan-jaff
|
79ab1aa35b
|
(fix) undo - model_dump_json() before logging
|
2024-01-05 11:47:16 +05:30 |
|
ishaan-jaff
|
40b9f1dcb1
|
(fix) proxy - log response before model_dump_json
|
2024-01-05 11:00:02 +05:30 |
|
ishaan-jaff
|
d1865591aa
|
(fix) test caching- use azure, instead of bedrock
|
2024-01-05 10:51:56 +05:30 |
|
Krrish Dholakia
|
6506fba3bc
|
test(test_proxy_exception_mapping.py): fix exception checking
|
2024-01-04 22:45:16 +05:30 |
|
Krrish Dholakia
|
25241de69e
|
fix(router.py): don't retry malformed / content policy violating errors (400 status code)
https://github.com/BerriAI/litellm/issues/1317 , https://github.com/BerriAI/litellm/issues/1316
|
2024-01-04 22:23:51 +05:30 |
|
Krrish Dholakia
|
aa72d65c90
|
fix(utils.py): fix check for if cached response should be returned
|
2024-01-04 21:49:19 +05:30 |
|
Krrish Dholakia
|
74f6f6489a
|
fix(proxy_server.py): fix prisma client connection error
|
2024-01-04 18:28:18 +05:30 |
|
Krrish Dholakia
|
6b708347f3
|
fix(proxy_server.py): enable sending test connections when slack alerting added to proxy via ui
|
2024-01-04 17:00:07 +05:30 |
|
Krrish Dholakia
|
c7644915f9
|
fix(test_proxy_server.py): fix import
|
2024-01-04 16:11:23 +05:30 |
|
Krrish Dholakia
|
263d20cdd0
|
fix(proxy_server.py): update proxy with full model list
|
2024-01-04 15:56:16 +05:30 |
|
Krrish Dholakia
|
773a0a147a
|
fix(utils.py): raise a bad request error if litellm client raises a model /provider not found error
|
2024-01-04 15:50:43 +05:30 |
|
Krrish Dholakia
|
99d9a825de
|
feat(proxy_server.py): abstract config update/writing and support persisting config in db
allows user to opt into writing to db (SAVE_CONFIG_TO_DB) and removes any api keys before sending to db
https://github.com/BerriAI/litellm/issues/1322
|
2024-01-04 14:44:59 +05:30 |
|
ishaan-jaff
|
c231a6e4d3
|
(ci/cd) run proxy test with debug=True
|
2024-01-04 13:01:00 +05:30 |
|
ishaan-jaff
|
234c057e97
|
(fix) azure+cf gateway, health check
|
2024-01-04 12:34:07 +05:30 |
|
Krrish Dholakia
|
b0827a87b2
|
fix(caching.py): support s-maxage param for cache controls
|
2024-01-04 11:41:23 +05:30 |
|
Krrish Dholakia
|
0f7d03f761
|
fix(proxy/rules.md): add docs on setting post-call rules on the proxy
|
2024-01-04 11:16:50 +05:30 |
|
ishaan-jaff
|
54653f9a4a
|
(test) proxy + s3 caching
|
2024-01-04 11:11:08 +05:30 |
|
ishaan-jaff
|
aa757d19f5
|
(test) router - init clients - azure cloudflare, openai etc
|
2024-01-04 10:55:18 +05:30 |
|
ishaan-jaff
|
0864713b62
|
(test) cf azure
|
2024-01-04 10:26:41 +05:30 |
|
ishaan-jaff
|
8e10a1eb81
|
(docs) config with cloudflare exampel
|
2024-01-04 10:25:35 +05:30 |
|
ishaan-jaff
|
6d21ee3a2f
|
(fix) proxy - cloudflare + Azure bug [non-streaming]
|
2024-01-04 10:24:51 +05:30 |
|
Dustin Miller
|
b10f64face
|
Adds "pre-fill" support for Claude
|
2024-01-03 18:45:36 -06:00 |
|
David Manouchehri
|
c54e0813b4
|
(caching) improve s3 backend by specifying cache-control and content-type
|
2024-01-03 13:44:28 -05:00 |
|
ishaan-jaff
|
30c6d164d2
|
(docs) use s3 Cache on litellm proxy
|
2024-01-03 17:56:44 +05:30 |
|
Krrish Dholakia
|
469ae0a378
|
fix(proxy/utils.py): don't keep connecting to db if connection already established
|
2024-01-03 17:43:44 +05:30 |
|
Krrish Dholakia
|
f2da345173
|
fix(caching.py): handle cached_response being a dict not json string
|
2024-01-03 17:29:27 +05:30 |
|
Krrish Dholakia
|
f2210787cd
|
feat(proxy_server.py): allow admins to update config via /config/update endpoint
|
2024-01-03 17:18:33 +05:30 |
|
ishaan-jaff
|
4680a26e2e
|
(test) proxy - load test
|
2024-01-03 16:16:18 +05:30 |
|
Krrish Dholakia
|
d45101b652
|
fix(proxy_server.py): fix master key reset, to preserve key from env
|
2024-01-03 16:10:10 +05:30 |
|
Krrish Dholakia
|
40c974999e
|
fix(proxy_server.py): reject bad /model/new POST requests
|
2024-01-03 15:54:58 +05:30 |
|
ishaan-jaff
|
d14a41863f
|
(test) s3 cache with setting s3_bucket_name
|
2024-01-03 15:42:23 +05:30 |
|
ishaan-jaff
|
58ce5d44ae
|
(feat) s3 cache support all boto3 params
|
2024-01-03 15:42:23 +05:30 |
|
Krrish Dholakia
|
b51371952b
|
fix(proxy_server.py): handle base case for /model/info
|
2024-01-03 15:33:29 +05:30 |
|
ishaan-jaff
|
fea0a933ae
|
(test) use s3 buckets cache
|
2024-01-03 15:13:43 +05:30 |
|
ishaan-jaff
|
00364da993
|
(feat) add s3 Bucket as Cache
|
2024-01-03 15:13:43 +05:30 |
|
Krrish Dholakia
|
14e501845f
|
fix(proxy_server.py): add support for setting master key via .env
|
2024-01-03 15:10:25 +05:30 |
|
Krrish Dholakia
|
ef8f1acfa4
|
refactor(proxy_server.py): more debug statements
|
2024-01-03 13:59:41 +05:30 |
|
Krrish Dholakia
|
8cee267a5b
|
fix(caching.py): support ttl, s-max-age, and no-cache cache controls
https://github.com/BerriAI/litellm/issues/1306
|
2024-01-03 12:42:43 +05:30 |
|
ishaan-jaff
|
2bea0c742e
|
(test) completion tokens counting + azure stream
|
2024-01-03 12:06:39 +05:30 |
|
ishaan-jaff
|
96cb6f3b10
|
(fix) azure+stream: count completion tokens
|
2024-01-03 12:06:39 +05:30 |
|
ishaan-jaff
|
f3b8d9c3ef
|
(fix) counting response tokens+streaming
|
2024-01-03 12:06:39 +05:30 |
|
Krrish Dholakia
|
cd98d256b5
|
fix(proxy_server.py): add alerting for responses taking too long
https://github.com/BerriAI/litellm/issues/1298
|
2024-01-03 11:18:21 +05:30 |
|
Krrish Dholakia
|
0d13c51615
|
fix(proxy/utils.py): fix self.alerting null case
https://github.com/BerriAI/litellm/issues/1298#issuecomment-1874798056
|
2024-01-03 10:12:21 +05:30 |
|
Krrish Dholakia
|
a778f8a00e
|
bump: version 1.16.10 → 1.16.11
|
2024-01-02 22:26:47 +05:30 |
|
Krrish Dholakia
|
070520d237
|
fix(proxy_server.py): support smtp email auth
previously was a hard resend package dependency. removed in favor of allowing any smtp server connection (including resend)
|
2024-01-02 22:22:19 +05:30 |
|
Ased Mammad
|
c39c8f70eb
|
fix(proxy_server.py) Check when '_hidden_params' is None
|
2024-01-02 19:04:51 +03:30 |
|
Krrish Dholakia
|
940569703e
|
feat(proxy_server.py): add slack alerting to proxy server
add alerting for calls hanging, failing and db read/writes failing
https://github.com/BerriAI/litellm/issues/1298
|
2024-01-02 17:45:18 +05:30 |
|
ishaan-jaff
|
c27b1fc5f8
|
(feat) proxy swagger - make admin link clickable
|
2024-01-02 17:04:32 +05:30 |
|
ishaan-jaff
|
14738ec89d
|
(test) xinference on litellm router
|
2024-01-02 16:51:08 +05:30 |
|