ishaan-jaff
|
cf82cd17e4
|
(temp) prisma client init logic
|
2024-01-09 13:00:23 +05:30 |
|
Krish Dholakia
|
a6d62409db
|
Update README.md
|
2024-01-09 12:59:57 +05:30 |
|
Krish Dholakia
|
f40c89ce00
|
Update README.md
|
2024-01-09 12:59:57 +05:30 |
|
Krish Dholakia
|
5360f8fd11
|
Update README.md
|
2024-01-09 12:59:57 +05:30 |
|
Krish Dholakia
|
ce6cf813f5
|
Update README.md
|
2024-01-09 12:59:57 +05:30 |
|
Krish Dholakia
|
67f233c603
|
Update README.md
|
2024-01-09 12:59:57 +05:30 |
|
Krish Dholakia
|
b1247f2d3b
|
Update README.md
|
2024-01-09 12:59:57 +05:30 |
|
Krish Dholakia
|
d707eae4df
|
Update README.md
|
2024-01-09 12:59:57 +05:30 |
|
Krrish Dholakia
|
73840806f8
|
build(model_prices_and_context_window.json): add max input tokens for openai and azure models
|
2024-01-09 12:59:57 +05:30 |
|
Krrish Dholakia
|
4946a301b2
|
build(model_prices_and_context_window.json): add max output tokens for openai + azure models, remove shutdown openai models
|
2024-01-09 12:59:57 +05:30 |
|
Krrish Dholakia
|
4bd459aef2
|
fix(openai.py): fix exception raising logic
|
2024-01-09 12:59:57 +05:30 |
|
Krrish Dholakia
|
d03b886079
|
fix(azure.py,-openai.py): raise the correct exceptions for image generation calls
|
2024-01-09 12:59:57 +05:30 |
|
Krrish Dholakia
|
27e52794df
|
fix(proxy_server.py): don't reconnect prisma if already connected
|
2024-01-09 12:59:57 +05:30 |
|
Krrish Dholakia
|
9673e6042e
|
test(test_router.py): fix router test
|
2024-01-09 12:59:42 +05:30 |
|
ishaan-jaff
|
d3f9a7df65
|
(fix) test - deprecated textdavinci003
|
2024-01-09 12:59:42 +05:30 |
|
ishaan-jaff
|
4791514351
|
(test) hosted - ollama catch timeouts
|
2024-01-09 12:59:42 +05:30 |
|
ishaan-jaff
|
77027746ba
|
(feat) litellm.completion - support ollama timeout
|
2024-01-09 12:59:42 +05:30 |
|
Krrish Dholakia
|
10f76ec36c
|
test: testing fixes
|
2024-01-09 12:59:42 +05:30 |
|
ishaan-jaff
|
520cd7fa89
|
(ci/cd) use 3 retries for image generation
|
2024-01-09 12:59:42 +05:30 |
|
ishaan-jaff
|
bae1323cb5
|
(ci/cd) pytest skip slow replicate test
|
2024-01-09 12:59:42 +05:30 |
|
Krrish Dholakia
|
32d1d64b63
|
refactor(lowest_latency.py): fix linting issue
|
2024-01-09 12:59:42 +05:30 |
|
Krrish Dholakia
|
832c10b402
|
feat(lowest_latency.py): support expanded time window for latency based routing
uses a 1hr avg. of latency for deployments, to determine which to route to
https://github.com/BerriAI/litellm/issues/1361
|
2024-01-09 12:59:42 +05:30 |
|
Krrish Dholakia
|
9dc2bc227b
|
refactor(lowest_latency.py): fix linting error
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
22a900463e
|
fix(ollama.py): use tiktoken as backup for prompt token counting
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
22e0a6c7df
|
docs(gemini.md): fix docs
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
9ddcdc4716
|
feat(lowest_latency.py): support expanded time window for latency based routing
uses a 1hr avg. of latency for deployments, to determine which to route to
https://github.com/BerriAI/litellm/issues/1361
|
2024-01-09 12:58:58 +05:30 |
|
HeavenHM
|
c6b9cf55b5
|
Update gemini.md
Added example for Gemini Vision Pro
|
2024-01-09 12:58:58 +05:30 |
|
Iskren Chernev
|
453c635d7b
|
Update deepinfra models
|
2024-01-09 12:58:58 +05:30 |
|
ishaan-jaff
|
7e9359ecb8
|
(ci/cd) run again
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
6197267e9a
|
build(Dockerfile): pip install from wheels not re-install requirements.txt
reduce size of dockerbuild
n
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
8913313bc1
|
test(test_proxy_startup.py): fix gunicorn test
|
2024-01-09 12:58:58 +05:30 |
|
Krish Dholakia
|
59511f9d4c
|
Update README.md
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
f875aae3c9
|
bump: version 1.16.19 → 1.16.20
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
834d3362d9
|
test(test_proxy_startup.py): separate tests
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
a37b40cdb9
|
fix(proxy_server.py): add support for passing in config file via worker_config directly + testing
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
a4f1f90497
|
build(Dockerfile.database): fix new dockerfile
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
4b4c2b0054
|
build(Dockerfile.database): fixing build issues
|
2024-01-09 12:58:58 +05:30 |
|
Krish Dholakia
|
f240ca0b57
|
Update ghcr_deploy.yml
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
30d738c83c
|
fix(proxy_server.py): improve /health/readiness endpoint to give more details on connected services
|
2024-01-09 12:58:58 +05:30 |
|
Krrish Dholakia
|
b061edf4d0
|
build(Dockerfile): new dockerfile with prisma db setup
not many services allow you to pass docker build args, so we needed another way of setting this
|
2024-01-09 12:58:58 +05:30 |
|
ishaan-jaff
|
87e69bb6f6
|
(temp) debug prisma logs
|
2024-01-08 19:21:18 +05:30 |
|
ishaan-jaff
|
6d1b0162fa
|
(fix) only run prisma generate when exception raised
|
2024-01-08 18:38:42 +05:30 |
|
ishaan-jaff
|
70c4b790b1
|
(chore) undo debug statement
|
2024-01-08 17:57:30 +05:30 |
|
ishaan-jaff
|
e7c62a4990
|
(temp) prisma client init logic
|
2024-01-08 17:56:54 +05:30 |
|
ishaan-jaff
|
84385ce80e
|
(fix) run prisma setup - on __init_
|
2024-01-08 17:54:51 +05:30 |
|
ishaan-jaff
|
9b04b1c9ad
|
(test) test key/generate against deployed proxy
|
2024-01-08 17:25:56 +05:30 |
|
ishaan-jaff
|
02c166138f
|
(test) test deployed endpoint
|
2024-01-08 17:17:31 +05:30 |
|
ishaan-jaff
|
5aaf1dd896
|
(fix) run prisma generate when it does not exist
|
2024-01-08 17:13:59 +05:30 |
|
ishaan-jaff
|
465d6f1b70
|
(temp) debug env variables for prisma setup
|
2024-01-08 16:45:14 +05:30 |
|
ishaan-jaff
|
8a5a8c2291
|
(temp) run prisma setup after intialize
|
2024-01-08 16:43:19 +05:30 |
|