Commit Graph
3734 Commits
Author SHA1 Message Date
Duc Pham 07e8cf1d9a Improved trimming logic and OpenAI token counter 2023-11-10 01:26:13 +07:00
ishaan-jaff a44aa8c10c (test) add proxy cli tests 2023-11-09 10:23:14 -08:00
Krrish Dholakia 9bfbdc18fb feat(utils.py): enable returning complete response when stream=true 2023-11-09 09:17:51 -08:00
ishaan-jaff cdb2474184 (cleanup) remove secrets template toml 2023-11-09 08:38:12 -08:00
ishaan-jaff c149829e1f run ci/cd again 2023-11-08 20:24:41 -08:00
Krrish Dholakia 84f68b2cd1 test(test_streaming.py): fix linting errors 2023-11-08 19:31:06 -08:00
Krrish Dholakia baa63deab7 bump: version 0.13.9 → 0.14.0 2023-11-08 19:27:35 -08:00
Krrish Dholakia 7ac9a632bd build(pyproject.toml): loosening openai dependency 2023-11-08 19:27:28 -08:00
Krrish Dholakia 182ca83912 bump: version 0.13.8 → 0.13.9 2023-11-08 19:24:56 -08:00
Krrish Dholakia 7c5fd5824b refactor(azure.py): fix linting errors 2023-11-08 19:24:53 -08:00
Krrish Dholakia 6f4707bbb3 refactor(azure.py): moving embeddings to http call 2023-11-08 19:07:21 -08:00
Krrish Dholakia 70311502c8 refactor(openai.py): moving embedding calls to http 2023-11-08 19:01:17 -08:00
Krrish Dholakia c2cbdb23fd refactor(openai.py): moving openai text completion calls to http 2023-11-08 18:40:03 -08:00
ishaan-jaff db0e032d53 (docs) simple proxy 2023-11-08 17:55:11 -08:00
ishaan-jaff fc05510a5d (docs) call specific model 2023-11-08 17:52:42 -08:00
ishaan-jaff fc45f41818 (docs) add instructions on running with FLASK 2023-11-08 17:48:14 -08:00
Krrish Dholakia c57ed0a9d7 refactor(openai.py): moving openai chat completion calls to http 2023-11-08 17:40:41 -08:00
ishaan-jaff da1451e493 (docs) use FLASK benchmarks with proxy 2023-11-08 17:25:59 -08:00
ishaan-jaff 68e668df13 (docs) lm harness 2023-11-08 17:21:12 -08:00
Krrish Dholakia 53abc31c27 refactor(azure.py): moving azure openai calls to http calls 2023-11-08 16:52:18 -08:00
ishaan-jaff 01a7660a12 (test) replicate with params 2023-11-08 14:28:06 -08:00
ishaan-jaff b102489f49 (docs) replicate input params 2023-11-08 14:23:37 -08:00
ishaan-jaff fe82e172b9 (fix) clean up proxy cli 2023-11-08 13:48:02 -08:00
Ishaan JaffandGitHub c63b09857c Update README.md 2023-11-08 13:39:29 -08:00
Ishaan JaffandGitHub e825de8b4e Update README.md 2023-11-08 13:37:30 -08:00
Ishaan JaffandGitHub af99f5f30b Update README.md 2023-11-08 13:37:02 -08:00
Ishaan JaffandGitHub cbe1414210 Update README.md 2023-11-08 13:31:40 -08:00
Ishaan JaffandGitHub cdd2a45600 Update README.md 2023-11-08 13:30:39 -08:00
Ishaan JaffandGitHub f00c2e6c16 readme proxy 2023-11-08 13:28:39 -08:00
ishaan-jaff 3498e881af (docs) proxy server 2023-11-08 13:27:17 -08:00
ishaan-jaff 50a1c55ce1 (docs) proxy 2023-11-08 13:24:21 -08:00
ishaan-jaff 57c78cebb9 (docs) proxy cli args 2023-11-08 13:19:25 -08:00
ishaan-jaff c6e4ea8558 (docs) proxy cli add params supported 2023-11-08 13:11:49 -08:00
ishaan-jaff 547f41071e (fix) proxy cli --test 2023-11-08 12:00:13 -08:00
ishaan-jaff 4dd7e2519f (test) add text completion steaming test 2023-11-08 11:59:31 -08:00
ishaan-jaff 2a751c277f (feat) add streaming for text_completion 2023-11-08 11:58:07 -08:00
ishaan-jaff a404b0fc3b (fix) remove errant print from hf 2023-11-08 11:49:15 -08:00
ishaan-jaff 6ee599545a (fix) text_completion don't pass echo to HF after translating 2023-11-08 11:45:05 -08:00
ishaan-jaff afea84e0c0 (test) run a test again 2023-11-08 10:34:57 -08:00
ishaan-jaff aba39670a3 (test) run ci/cd again 2023-11-08 10:21:19 -08:00
ishaan-jaff 55eb274f36 (test) remove dup hf test 2023-11-08 09:54:40 -08:00
ishaan-jaff b8ebab5d4f (test) router functionality 2023-11-08 09:48:48 -08:00
ishaan-jaff 39ca8b5043 bump: version 0.13.7 → 0.13.8 2023-11-08 09:46:57 -08:00
Ishaan JaffandGitHub 8cedacfa2d Merge pull request #781 from clalanliu/main
fix: fix bug for the case --model is not specified
2023-11-08 08:26:32 -08:00
Alan Liu 6c17ab6e75 fix: fix bug for the case --model is not specified 2023-11-08 23:57:24 +08:00
ishaan-jaff 3239ec80c9 (docs) embedding models 2023-11-07 21:43:02 -08:00
Krrish Dholakia e7735274de fix(factory.py): fixing llama-2 non-chat models prompt templating 2023-11-07 21:33:54 -08:00
Krrish Dholakia ce27e08e7d (fix): llama-2 non-chat models prompt template 2023-11-07 21:33:54 -08:00
ishaan-jaff 4ca4038246 (docs) proxy server 2023-11-07 17:27:58 -08:00
ishaan-jaff febb163850 (docs) proxy server openai api base 2023-11-07 17:24:47 -08:00