Laurel Orr
a6a774bfb8
fix: handle none connectionstr ( #110 )
1 year ago
Laurel Orr
d94101964f
fix: add gpt 16k ( #109 )
1 year ago
Laurel Orr
49f51952df
fix: dummy client to output tokens and random responses ( #106 )
1 year ago
Yuval
b775d15f2e
fix: Updated AI21 models from J1 to J2 ( #104 )
...
also, added ai21 example to README
Co-authored-by: Yuval Belfer <yuvalb@ai21.com>
1 year ago
Laurel Orr
fd7fbc9e35
fix: lru cache HF get model params ( #105 )
1 year ago
Laurel Orr
b745617045
fix: add trust remote code HF models ( #102 )
1 year ago
Laurel Orr
7285fee140
chore: bump version ( #101 )
1 year ago
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 )
2 years ago
Laurel Orr
0fb192a0a2
feat: add local huggingface embedding models ( #76 )
2 years ago
Laurel Orr
40de0e7f59
feat: openai embedding support ( #75 )
2 years ago
Laurel Orr
693d105106
chore: bump version ( #74 )
2 years ago
Laurel Orr
c7906bead5
fix: add retry to client for ratelimit ( #73 )
2 years ago
Laurel Orr
ee9f16688e
chore: reformat openaichat ( #72 )
2 years ago
Sasha Rush
d7b83d94bd
Update openaichat.py ( #70 )
...
Add gpt4 endpoints
2 years ago
Laurel Orr
e4d3a57f92
fix: added openai usage back ( #69 )
2 years ago
Laurel Orr
395ac06a95
feat: async support, openai chatgpt, batch cache fix ( #68 )
2 years ago
Sabri Eyuboglu
bed6773f75
Hash postgres keys to support long documents ( #62 )
...
* [WIP] Hash the cache key in postgres
* [WIP] Format
2 years ago
Sabri Eyuboglu
e00d285e21
Add PostgreSQL cache ( #53 )
...
Add a Cache for PostgreSQL with GCP.
Co-authored-by: Laurel Orr <lorr1@cs.stanford.edu>
2 years ago
Laurel Orr
c4ad007f02
feat: support token_logprobs ( #59 )
2 years ago
Laurel Orr
c6331770d4
chore: bump version ( #57 )
2 years ago
Laurel Orr
ace3ad4324
chore: fix manifest imports ( #56 )
2 years ago
Laurel Orr
8ced666df8
fix: add dtype to cache ( #52 )
2 years ago
Laurel Orr
e351bd5315
Update README.md citation
2 years ago
Laurel Orr
504e0e6cf1
chore: fix precommit ( #51 )
2 years ago
Laurel Orr
94b57a6e6f
feat: remove choice logits and use prompt scoring ( #50 )
2 years ago
Laurel Orr
876d27bd2d
feat: toma diffusers support ( #48 )
2 years ago
Laurel Orr
56eae406ce
feat: chatgpt client added ( #47 )
2 years ago
Laurel Orr
defc63bf36
feat: web app for manifest ( #46 )
...
Also fixed typing issues in tests
2 years 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>
2 years 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
2 years ago
Laurel Orr
88a05ec09e
fix: update toma API ( #44 )
...
* fix: update toma API
Added langchain demo notebook
* build: fix isort python 310
2 years ago