 Jyong
|
60ee98f578
zhipu embedding token method (#1976)
|
1 year ago |
 Charlie.Wei
|
5b24d7129e
Azure openai init (#1929)
|
1 year ago |
 Bowen Liang
|
b8592ad412
fix: indentation violations in YAML files (#1972)
|
1 year ago |
|
Bowen Liang
|
e696b72f08
web: requires NodeJs 18.17 at minimum for NextJs 14 (#1974)
|
1 year ago |
 Chenhe Gu
|
344821ed35
enforce utf-8 encoding for provider response (#1973)
|
1 year ago |
|
Bowen Liang
|
126b4c332f
web: bump Next.js to 14.0 for faster local server startup (#1925)
|
1 year ago |
|
Bowen Liang
|
c32c177e15
improvement: introduce Super-Linter actions to check style for shell script, dockerfile and yaml files (#1966)
|
1 year ago |
 zxhlyh
|
853cdd741f
fix: update model list (#1967)
|
1 year ago |
|
Bowen Liang
|
69d42ae95b
fix: cover missed source paths for eslint (#1956)
|
1 year ago |
|
Chenhe Gu
|
5ff701ca3f
correct xorbits spelling (#1965)
|
1 year ago |
 takatost
|
9f58912fd7
bump version to 0.4.4 (#1962)
|
1 year ago |
|
takatost
|
0c746f5c5a
fix: generate not stop when pressing stop link (#1961)
|
1 year ago |
 Garfield Dai
|
a8cedea15a
fix: check result should be string. (#1959)
|
1 year ago |
|
Chenhe Gu
|
87832ede17
delete remnant 'required': false (#1955)
|
1 year ago |
|
Jyong
|
4d99c689f0
prohibit enable and disable function when segment is not completed (#1954)
|
1 year ago |
|
Jyong
|
28b26f67e2
optimize qa prompt (#1957)
|
1 year ago |
|
Chenhe Gu
|
b934232411
change API key field to 'required' (#1953)
|
1 year ago |
|
takatost
|
2f120786fd
feat: reorder togetherai (#1951)
|
1 year ago |
|
Chenhe Gu
|
6075fee556
Add Together.ai's OpenAI API-compatible inference endpoints (#1947)
|
1 year ago |
|
Chenhe Gu
|
de584807e1
fix streaming (#1944)
|
1 year ago |
|
zxhlyh
|
a1285cbf15
fix: text-generation run batch (#1945)
|
1 year ago |
|
Garfield Dai
|
cf1f6f3961
fix: text completion app cannot get data. (#1942)
|
1 year ago |
|
takatost
|
f4d97ef9fa
fix: arg user required and must not be null in service generate api (#1943)
|
1 year ago |
|
takatost
|
28883e80d4
fix: gpt-4-32k model name empty in OpenAI response (#1941)
|
1 year ago |
|
takatost
|
a0f74cdd9d
fix: llm result usage none (#1940)
|
1 year ago |
|
takatost
|
296bf443a8
feat: reuse decoding_rsa_key & decoding_cipher_rsa & optimize construct (#1937)
|
1 year ago |
|
takatost
|
af7be9bdd7
Feat/optimize entity construct (#1935)
|
1 year ago |
|
takatost
|
2cfd5568e1
fix: vision fail in complete app (#1933)
|
1 year ago |
|
takatost
|
faf40a42bc
feat: optimize memory & invoke error output (#1931)
|
1 year ago |
|
takatost
|
97c972f14d
feat: bump version 0.4.3 (#1930)
|
1 year ago |
