Krrish Dholakia
e904a84bdb
build: reintegrate mypy linting in pre-commit hook
2024-03-21 08:09:02 -07:00
Krrish Dholakia
2ce5de903f
fix: fix linting issue
2024-03-21 08:05:47 -07:00
Krrish Dholakia
d91f9a9f50
feat(proxy_server.py): enable llm api based prompt injection checks
...
run user calls through an llm api to check for prompt injection attacks. This happens in parallel to th
e actual llm call using `async_moderation_hook`
2024-03-20 22:43:42 -07:00
Krrish Dholakia
f24d3ffdb6
fix(proxy_server.py): fix import
2024-03-20 19:15:06 -07:00
Krrish Dholakia
3bb0e24cb7
fix(prompt_injection_detection.py): ensure combinations are actual phrases, not just 1-2 words
...
reduces misflagging
https://github.com/BerriAI/litellm/issues/2601
2024-03-20 19:09:38 -07:00
Ishaan Jaff
285084e4be
bump: version 1.32.8 → 1.32.9
2024-03-20 17:05:00 -07:00
Ishaan Jaff
7654400a10
Merge pull request #2609 from BerriAI/litellm_docs_using_cache_ping
...
[docs] using /cache/ping
2024-03-20 17:04:38 -07:00
Ishaan Jaff
5842486810
(docs) using /cache/ping
2024-03-20 17:03:26 -07:00
Ishaan Jaff
1d63e05e6c
bump: version 1.32.7 → 1.32.8
2024-03-20 16:54:23 -07:00
Ishaan Jaff
8aba161821
Merge pull request #2605 from BerriAI/litellm_fix_num_workers_issue
...
(fix) start proxy with default num_workers=1
2024-03-20 16:44:06 -07:00
Ishaan Jaff
c068a5fb74
(docs) deploying litellm
2024-03-20 11:47:55 -07:00
Ishaan Jaff
3ad6e5ffc1
(feat) start proxy with default num_workers=1
2024-03-20 10:46:32 -07:00
Ishaan Jaff
cace0bd6fb
(fix) self.redis_version issue
2024-03-20 10:36:08 -07:00
Ishaan Jaff
7b29273b14
(fix) redis 6.2 version incompatibility issue
2024-03-20 09:38:21 -07:00
Krrish Dholakia
ca970a90c4
fix(handle_jwt.py): remove issuer check
2024-03-20 08:35:23 -07:00
Ishaan Jaff
909883ee04
Merge pull request #2602 from BerriAI/litellm_cache_ping
...
(feat) litellm proxy /cache/ping
2024-03-20 08:32:14 -07:00
Ishaan Jaff
4ed551dc52
(feat) better debugging for /cache/ping
2024-03-20 08:30:11 -07:00
Ishaan Jaff
2256ece5a9
(feat) litellm cache ping
2024-03-20 08:24:13 -07:00
Krrish Dholakia
88733fda5d
docs(prompt_injection.md): open sourcing prompt injection detection
2024-03-19 22:48:52 -07:00
Krrish Dholakia
524c244dd9
fix(utils.py): support response_format param for ollama
...
https://github.com/BerriAI/litellm/issues/2580
2024-03-19 21:07:20 -07:00
Krrish Dholakia
d6624bf6c3
refactor(main.py): trigger new build
2024-03-19 21:05:53 -07:00
Krish Dholakia
f6bab298a0
Updated config.yml
2024-03-19 21:04:38 -07:00
Ishaan Jaff
8f750b71eb
(fix) caching - don't require cache password
2024-03-19 20:50:16 -07:00
Krrish Dholakia
dff4d6363a
bump: version 1.32.6 → 1.32.7
2024-03-19 20:42:38 -07:00
Krrish Dholakia
066346b8c8
test: handle flaky tests locally - causing db timeout issues on circle ci
2024-03-19 20:39:53 -07:00
Krrish Dholakia
f25b03326b
fix(proxy_server.py): allow user to disable scheduled reset budget task
2024-03-19 20:36:22 -07:00
Krrish Dholakia
2dfdc8dd69
Revert "Merge pull request #2593 from BerriAI/litellm_reset_budget_fix"
...
This reverts commit afd363129fc94bc94ad5
2024-03-19 20:25:41 -07:00
Krrish Dholakia
3a866dd349
bump: version 1.32.5 → 1.32.6
2024-03-19 20:17:50 -07:00
Krish Dholakia
afd363129f
Merge pull request #2593 from BerriAI/litellm_reset_budget_fix
...
fix(proxy/utils.py): fix reset budget logic
2024-03-19 20:17:03 -07:00
Krrish Dholakia
b9f222f8fb
test(test_users.py): skip flaky circle ci test
2024-03-19 20:09:38 -07:00
Krrish Dholakia
37795c0d92
fix(proxy_server.py): add more debug logs
2024-03-19 19:59:43 -07:00
Krrish Dholakia
97e7113b87
test(test_users.py): fix test
2024-03-19 19:48:44 -07:00
Krrish Dholakia
9140453d0c
test: make test call more reliable
2024-03-19 19:47:18 -07:00
Krrish Dholakia
0822f6283f
test(test_users.py): reposition test
...
trying to identify why endpoint isn't being called
2024-03-19 19:40:41 -07:00
Krrish Dholakia
f6de3a0359
fix: better debug logs
2024-03-19 19:28:26 -07:00
Ishaan Jaff
c94bc94ad5
Merge pull request #2591 from BerriAI/litellm_metrics_endpoint
...
[Feat] /metrics endpoint for Prometheus, Grafana
2024-03-19 18:08:22 -07:00
Krrish Dholakia
e0d3b18835
fix(proxy/utils.py): fix reset budget logic
...
uses fewer clients - prevents read timeouts
2024-03-19 18:02:09 -07:00
Ishaan Jaff
827a8af093
(fix) add prometheus_client to req.txt
2024-03-19 18:01:04 -07:00
Krish Dholakia
5171d7689f
Merge pull request #2592 from BerriAI/litellm_jwt_auth
...
feat(handle_jwt.py): support authenticating admins into the proxy via jwt's
2024-03-19 17:54:54 -07:00
Krrish Dholakia
3ed3d89a06
docs: doc cleanup
2024-03-19 17:50:31 -07:00
Krrish Dholakia
0c1d754e2c
docs(cost_tracking.md): cleanup docs
2024-03-19 17:40:52 -07:00
Krrish Dholakia
191c2256f6
docs(deploy.md): fix deploy quick start command
2024-03-19 17:35:08 -07:00
Krrish Dholakia
749ebae124
build(requirements.txt): cleanup
2024-03-19 17:33:53 -07:00
Ishaan Jaff
bed1c0478a
(fix) include prom endpoint
2024-03-19 17:30:07 -07:00
Ishaan Jaff
c196186190
(fix) add /metrics to utils.py
2024-03-19 17:28:33 -07:00
Krrish Dholakia
1c68a7fd1d
refactor(handle_jwt.py): print jwt version
2024-03-19 17:17:11 -07:00
Krrish Dholakia
9ce7aeab67
build: fix build
2024-03-19 17:09:23 -07:00
Krrish Dholakia
8c91156842
build: build fixes
2024-03-19 16:59:59 -07:00
Krrish Dholakia
a8d3d51d21
docs(token_based_auth.md): add jwt auth to docs
2024-03-19 16:34:27 -07:00
Krrish Dholakia
7aff716c68
build(requirements.txt): add jwt to docker requirements
2024-03-19 16:23:24 -07:00
