Krrish Dholakia
01a1a8f731
fix(caching.py): dual cache async_batch_get_cache fix + testing
...
this fixes a bug in usage-based-routing-v2 which was caused b/c of how the result was being returned from dual cache async_batch_get_cache. it also adds unit testing for that function (and it's sync equivalent)
2024-04-19 15:03:25 -07:00
Krrish Dholakia
9c42c847a5
fix(router.py): instrument pre-call-checks for all openai endpoints
2024-04-18 21:54:25 -07:00
Krrish Dholakia
81573b2dd9
fix(test_lowest_tpm_rpm_routing_v2.py): unit testing for usage-based-routing-v2
2024-04-18 21:38:00 -07:00
Krrish Dholakia
a05f148c17
fix(tpm_rpm_routing_v2.py): fix tpm rpm routing
2024-04-18 20:01:22 -07:00
Krrish Dholakia
f65005f273
fix(caching.py): fix error logging
2024-04-18 17:21:10 -07:00
Krrish Dholakia
0afb5d6573
fix(caching.py): add call type to service logger object
2024-04-18 16:53:34 -07:00
Krrish Dholakia
0f95a824c4
feat(prometheus_services.py): emit proxy latency for successful llm api requests
...
uses prometheus histogram for this
2024-04-18 16:04:35 -07:00
Krrish Dholakia
bef24cd4ab
fix(caching.py): don't decode a string
2024-04-13 18:48:03 -07:00
Krrish Dholakia
4e81acf2c6
feat(prometheus_services.py): monitor health of proxy adjacent services (redis / postgres / etc.)
2024-04-13 18:15:02 -07:00
Krrish Dholakia
c03b0bbb24
fix(router.py): support pre_call_rpm_check for lowest_tpm_rpm_v2 routing
...
have routing strategies expose an ‘update rpm’ function; for checking + updating rpm pre call
2024-04-12 18:25:14 -07:00
Krrish Dholakia
76bd667b12
fix(caching.py): fix async batch redis get request
2024-04-10 21:37:45 -07:00
Krrish Dholakia
180cf9bd5c
feat(lowest_tpm_rpm_v2.py): move to using redis.incr and redis.mget for getting model usage from redis
...
makes routing work across multiple instances
2024-04-10 14:56:23 -07:00
Ishaan Jaff
c4cb0afa98
feat - delete cache key
2024-04-04 10:56:47 -07:00
Krish Dholakia
7233e5ab25
Merge pull request #2789 from BerriAI/litellm_set_ttl
...
fix(proxy_server.py): allow user to set in-memory + redis ttl
2024-04-02 08:53:34 -07:00
Krrish Dholakia
203e2776f8
fix(proxy_server.py): allow user to set in-memory + redis ttl
...
addresses - https://github.com/BerriAI/litellm/issues/2700
2024-04-01 19:13:23 -07:00
Ishaan Jaff
4ebb4570be
(fix) handle urls correctly
2024-04-01 17:08:48 -07:00
Ishaan Jaff
916e4032ee
redis show client_list, info
2024-04-01 16:54:42 -07:00
Krrish Dholakia
5926792de6
fix(caching.py): respect redis namespace for all redis get/set requests
2024-03-30 20:20:29 -07:00
Krrish Dholakia
f58fefd589
fix(tpm_rpm_limiter.py): enable redis caching for tpm/rpm checks on keys/user/teams
...
allows tpm/rpm checks to work across instances
https://github.com/BerriAI/litellm/issues/2730
2024-03-30 20:01:36 -07:00
Ishaan Jaff
098a03facc
(fix) undo changes from other branches
2024-03-26 09:22:19 -07:00
Ishaan Jaff
b8af946fb9
(feat) /cache/flushall
2024-03-26 09:18:58 -07:00
Ishaan Jaff
ade5d58331
(fix) in mem redis reads
2024-03-26 09:10:49 -07:00
Ishaan Jaff
553ac19f9f
(feat) improve cache debugging litellm
2024-03-25 18:26:58 -07:00
Ishaan Jaff
32d4756943
(fix) print verbose in batch writing redis
2024-03-25 18:02:31 -07:00
Ishaan Jaff
7134d66fae
Merge branch 'main' into litellm_batch_write_redis_cache
2024-03-25 16:41:29 -07:00
Ishaan Jaff
abce689862
(feat) batch write redis cache output
2024-03-25 16:39:47 -07:00
Ishaan Jaff
37aadba959
(feat) v0 batch redis cache writes
2024-03-25 15:20:10 -07:00
Krrish Dholakia
591a0a376e
fix(caching.py): support default ttl for caching
2024-03-25 13:40:17 -07:00
Krish Dholakia
007d439017
Merge pull request #2606 from BerriAI/litellm_jwt_auth_updates
...
fix(handle_jwt.py): track spend for user using jwt auth
2024-03-20 19:40:17 -07:00
Krrish Dholakia
8bb00c4ae8
fix(caching.py): enable async setting of cache for dual cache
2024-03-20 18:42:34 -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
Ishaan Jaff
2256ece5a9
(feat) litellm cache ping
2024-03-20 08:24:13 -07:00
Krrish Dholakia
03acc07380
fix(caching.py): pass redis kwargs to connection pool init
2024-03-18 08:21:36 -07:00
Krrish Dholakia
48f96dd563
fix(caching.py): close redis connection pool upon proxy shutdown
2024-03-16 10:39:58 -07:00
Krrish Dholakia
3072137739
test(test_caching.py): fix async tests
2024-03-15 18:09:25 -07:00
Krrish Dholakia
226953e1d8
feat(batch_redis_get.py): batch redis GET requests for a given key + call type
...
reduces the number of GET requests we're making in high-throughput scenarios
2024-03-15 14:40:11 -07:00
Krrish Dholakia
7c72cc0ec9
fix(caching.py): support redis caching with namespaces
2024-03-14 13:35:17 -07:00
Krrish Dholakia
d6537a05ca
fix(caching.py): fix print statements
2024-03-14 12:58:34 -07:00
Krrish Dholakia
1b807fa3f5
fix(proxy_server.py): fix key caching logic
2024-03-13 19:10:24 -07:00
Krish Dholakia
c7d0af0a2e
Merge pull request #2426 from BerriAI/litellm_whisper_cost_tracking
...
feat: add cost tracking + caching for `/audio/transcription` calls
2024-03-09 19:12:06 -08:00
ishaan-jaff
1917ee7fcf
(feat) debug when in meory cache is used
2024-03-09 16:24:04 -08:00
Krrish Dholakia
9b7c8880c0
fix(caching.py): only add unique kwargs for transcription_only_kwargs in caching
2024-03-09 16:09:12 -08:00
Krrish Dholakia
fa45c569fd
feat: add cost tracking + caching for transcription calls
2024-03-09 15:43:38 -08:00
Krrish Dholakia
726dad5756
fix(caching.py): add s3 path as a top-level param
2024-03-06 18:07:28 -08:00
Krrish Dholakia
fb2ae3a032
fix(utils.py): only return cached streaming object for streaming calls
2024-02-21 21:27:40 -08:00
Krrish Dholakia
74381a2d06
fix(caching.py): use print verbose for logging error
2024-02-15 18:12:09 -08:00
Krrish Dholakia
66c7e35a97
fix(redis.py): fix instantiating redis client from url
2024-02-15 17:48:00 -08:00
ishaan-jaff
d87c4a4d23
(fix) s3 cache proxy - fix notImplemented error
2024-02-13 16:34:43 -08:00
ishaan-jaff
8197b3de0a
(fix) remove extra statement
2024-02-07 19:24:27 -08:00
