Commit Graph

102 Commits (ceb8676c3303f1088b944edb60445a2b96031947)
 

Author SHA1 Message Date
Laurel Orr ceb8676c33
chore: fix comments (#100) 1 year ago
Laurel Orr 6324e0fe43
feat: streaming support completions (#99) 1 year ago
Laurel Orr b52a4d9a4b
Laurel/more models (#98)
* fix: google models

* fix: azure models and refactor
1 year ago
Laurel Orr 4903c7e7e8
chore: bump version (#97) 1 year ago
Laurel Orr fd6e3d965b
Laurel/chatgpt hotfix (#96)
* fix: chatgpt hotfix

* chore: fix retry test
1 year ago
Laurel Orr 93ff2cb3c1
fix: chatgpt hotfix (#95) 1 year ago
Laurel Orr af23272cb5
fix: chatgpt hotfix (#94) 1 year ago
Laurel Orr 63943a5d3e
chore: bump version (#93) 1 year ago
Laurel Orr 147436c9b2
feat: unify run_chat and run (#92) 1 year ago
Laurel Orr 5ad4b017b5
wip: lore huggingface eval (#91) 1 year ago
Laurel Orr 97f3ec557b
chore: bump version (#89) 1 year ago
Laurel Orr 8548329be9
feat: added run_chat for chat models (#88) 1 year ago
Laurel Orr afe0fc5a1d
feat: added run_chat for chat models (#87) 1 year ago
Laurel Orr c0b4644a1c
chore: bump version (#86) 1 year ago
Laurel Orr e559c8fa59
fix: logprobs from openai (#85) 1 year ago
Laurel Orr d7401c6ec5
fix: added pydantic types to response (#84) 1 year ago
Laurel Orr 4602fb919b
chore: update readme (#82) 1 year ago
Laurel Orr db963cf4a7 fix: added client pool support (#81)
* fix: added client pool support

* Added async across client pool
1 year ago
Laurel Orr d375ef0c74 chore: bump version (#80) 1 year ago
Laurel Orr f2e6ec9984 chore: try catch around retry error (#77) 1 year ago
Laurel Orr 0fb192a0a2 feat: add local huggingface embedding models (#76) 1 year ago
Laurel Orr 40de0e7f59 feat: openai embedding support (#75) 1 year ago
Laurel Orr 693d105106 chore: bump version (#74) 1 year ago
Laurel Orr c7906bead5 fix: add retry to client for ratelimit (#73) 1 year ago
Laurel Orr ee9f16688e chore: reformat openaichat (#72) 1 year ago
Sasha Rush d7b83d94bd Update openaichat.py (#70)
Add gpt4 endpoints
1 year ago
Laurel Orr e4d3a57f92 fix: added openai usage back (#69) 1 year ago
Laurel Orr 395ac06a95 feat: async support, openai chatgpt, batch cache fix (#68) 1 year ago
Sabri Eyuboglu bed6773f75 Hash postgres keys to support long documents (#62)
* [WIP] Hash the cache key in postgres

* [WIP] Format
1 year ago
Sabri Eyuboglu e00d285e21 Add PostgreSQL cache (#53)
Add a Cache for PostgreSQL with GCP. 

Co-authored-by: Laurel Orr <lorr1@cs.stanford.edu>
1 year ago
Laurel Orr c4ad007f02 feat: support token_logprobs (#59) 1 year ago
Laurel Orr c6331770d4 chore: bump version (#57) 1 year ago
Laurel Orr ace3ad4324 chore: fix manifest imports (#56) 1 year ago
Laurel Orr 8ced666df8 fix: add dtype to cache (#52) 1 year ago
Laurel Orr e351bd5315 Update README.md citation 1 year ago
Laurel Orr 504e0e6cf1 chore: fix precommit (#51) 1 year ago
Laurel Orr 94b57a6e6f feat: remove choice logits and use prompt scoring (#50) 1 year ago
Laurel Orr 876d27bd2d feat: toma diffusers support (#48) 1 year ago
Laurel Orr 56eae406ce feat: chatgpt client added (#47) 1 year ago
Laurel Orr defc63bf36 feat: web app for manifest (#46)
Also fixed typing issues in tests
1 year ago
Laurel Orr 6f5b64f0df Laurel/diffusion (#40)
* Sketch of diffusers added

* [WIP] Array caching implemented with end2end diffusion working

* [WIP] Make initial pass on CLIP model

* [WIP] Get endpoint running for CLIP

* Add support for clip images

* [chore] merge main

* chore: fix xxhash install

Co-authored-by: Sabri Eyuboglu <eyuboglu@stanford.edu>
1 year ago
Laurel Orr 26e440b6a6 Laurel/toma langchain (#45)
* fix: update toma API

Added langchain demo notebook

* build: fix isort python 310

* chore: refactor example chain
1 year ago
Laurel Orr 88a05ec09e fix: update toma API (#44)
* fix: update toma API

Added langchain demo notebook

* build: fix isort python 310
1 year ago
Laurel Orr a9d8bdd4dc [feature] added galactica models, improved response error handling (#41) 2 years ago
Laurel Orr e86b8e81bf [feat] batch run; remove prompt batch_run zoo and opt; refactor to us… (#39)
* [feat] batch run; remove prompt batch_run zoo and opt; refactor to use standard request inputs

* [chore] test rounding fix
2 years ago
Laurel Orr a4cd201b8e Deepspeed (#38)
* [feat] deepspeed and batch support huggingface api

* [chore] add deepspeed to readme

* [chore] fix hf api test
2 years ago
Laurel 8b423d6962 v0.0.1 release 2 years ago
Laurel 37a232ef7d [chore] fix readme install 2 years ago
Laurel 073f8117c8 [chore] add runid test 2 years ago
Laurel Orr c5f00b9f73 Request cache refactor (#37)
* [wip] cache import clean up and removed api imports

* [chore] add timeout to requests

* [chore] toma heartbeats to logger
2 years ago