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
e559c8fa59
fix: logprobs from openai ( #85 )
1 year ago
Laurel Orr
d7401c6ec5
fix: added pydantic types to response ( #84 )
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
40de0e7f59
feat: openai embedding support ( #75 )
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
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
88a05ec09e
fix: update toma API ( #44 )
...
* fix: update toma API
Added langchain demo notebook
* build: fix isort python 310
1 year 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
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
Laurel Orr
457a4aaa68
fix: mypy fix openai
2 years ago
Parth Thakkar
24b92445d2
Add rate limit handler for OpenAI ( #25 )
...
Signed-off-by: Parth Thakkar <parthdt2@illinois.edu>
Signed-off-by: Parth Thakkar <parthdt2@illinois.edu>
2 years ago
Laurel Orr
5428afdc58
Zoo ( #23 )
...
* Zoo Model
* Remove optional import zoo
* Read model name from zoo model
* Logprobs passed through raw response for gold choices
Co-authored-by: Simran <emailsimran@gmail.com>
Co-authored-by: Dan Fu <danfu@cs.stanford.edu>
2 years ago
Laurel Orr
d610e3c800
Laurel/dev ( #20 )
...
* fix: added perc gpu memory reduction flag app
* fix: removed poetry and standardized api inputs
* Removed poetry and use setup.py
* Addressing https://github.com/HazyResearch/manifest/issues/16
2 years ago
Laurel Orr
c04aa1e62c
fix: ai21 prompt added with logprobs
2 years ago
Laurel Orr
f568875e57
fix: fixing https://github.com/HazyResearch/manifest/issues/7 and https://github.com/HazyResearch/manifest/issues/5
2 years ago
ANarayan
ad6a27c1f9
[add] codex endpoints
2 years ago
Laurel Orr
894042c370
[feature] added opt; better kwargs for errors
2 years ago
Laurel Orr
bf16963f3d
[feature] redis DB, flask API, tests
2 years ago
Laurel Orr
ed301be2a7
First main commit
2 years ago