AVB/bedrock-access-gateway
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
93 Commits 2 Branches 0 Tags
1cb8a6a6037db390e430a97f4fcdbcc87d3d11aa
Commit Graph

51 Commits

Author SHA1 Message Date
Aiden Dai
c39f6bc942 Use secrets manager for api key 2025-02-10 15:25:12 +08:00
yytdfc
093c6fa586 add stop parameter (#86) 2024-12-31 11:15:24 +08:00
Aiden Dai
b2c187c716 Increase connect timeout 2024-12-19 16:45:18 +08:00
Aiden Dai
51bc727b38 Use readme 2024-12-16 17:11:54 +08:00
Aiden Dai
29621ae59c Automatically detect model list 2024-12-16 16:15:09 +08:00
Aiden Dai
d4938a0af2 Automatically detect model list 2024-12-16 16:01:59 +08:00
Attila Szucs
cb38d328aa Add environment variable for PORT (#47) 
* Customizable port

* Fix CMD
 2024-12-16 10:00:17 +08:00
Fabio Nonato
4fc0d3bc94 Image error fix (#80) 
---------

Co-authored-by: Fabio Nonato <fnp@amazon.com>
 2024-12-11 11:26:51 +08:00
Hans Knecht
241d5c0f3e feat: allow the use of an ENV variable to set the API key if the ParameterStore isn't used. (#40) 2024-12-06 14:32:06 +08:00
Fabian Fischer
25b3cfb146 feat: add amazon nova inference profiles in us (#79) 2024-12-06 13:52:50 +08:00
mschfh
17503b032a Add cross-region inference profiles for Llama 3.2 models. (#75) 2024-12-05 11:22:11 +08:00
bkocik
6849ca828a Add cross-region inference profiles for Llama 3.1 models. (#72) 2024-11-20 09:57:35 +08:00
KAEYL98
11a31b5584 feat: add support for APAC claude 3 profiles (#69) 2024-11-07 16:43:15 +08:00
heisenbergye
5f7676608a suppot all Claude models Cross-Region Inference (#65) 2024-10-29 14:43:31 +08:00
Sergei Mikhailov
3a97677b97 Added "new Claude 3.5 Sonnet" v2 model to the list (#60) 2024-10-23 14:54:45 +08:00
Meng Xin Zhu
c1ee1b4244 chore: add automation script to release images (#58) 2024-10-09 18:20:14 +08:00
Yuki Sekiya
c655f50616 feat: Handle multiple user messages in a single request (#26) 2024-10-09 15:13:58 +08:00
diopres
db0817392f feat: add support for Mistral Large 2 (24.07) 
added support for Mistral Large 2 (24.07)
 2024-08-12 19:06:44 +05:30
Aiden Dai
2950c15ecb Fix empty response bug 2024-08-09 17:28:09 +08:00
Aiden Dai
f8faf32a76 Add Llama 3.1 without tool call 2024-07-30 12:27:08 +08:00
Aiden Dai
f6b73152bc Update boto3 version 2024-06-25 17:29:47 +08:00
Aiden Dai
66bdfdf5c1 Support Claude 3.5 Sonnet 2024-06-21 10:28:04 +08:00
Aiden Dai
49dd6608a0 Support of tool choice 2024-06-21 10:24:11 +08:00
Aiden Dai
b3509ee0f0 Support multiple tool calls 2024-06-11 16:58:26 +08:00
Aiden Dai
56786f9e32 Update api response 2024-06-11 10:53:56 +08:00
Aiden Dai
6ef7641a0d Update api response 2024-06-07 10:58:44 +08:00
Aiden Dai
5f84cef13a Refactor to use new Converse API 2024-06-04 17:01:06 +08:00
Aiden Dai
f0ea117732 Refactor to use new Converse API 2024-06-04 16:20:25 +08:00
Aiden Dai
696039053d Refactor to use new Converse API 2024-06-04 14:59:40 +08:00
dependabot[bot]
c7276171ad --- 
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
 2024-05-21 08:06:48 +00:00
Aiden Dai
9f6b334385 Refactor model implementation 2024-05-09 16:58:04 +08:00
Aiden Dai
180c199da9 Add base64 encoded embedding support 2024-04-26 13:46:46 +08:00
Aiden Dai
0512a9b8cc Add Llama 3 support 2024-04-23 10:30:57 +08:00
Aiden Dai
7416f9a4e2 Clean up code 2024-04-18 16:22:06 +08:00
yhx
7df5617037 Add support of anthropic.claude-3-opus-20240229-v1:0 model 2024-04-17 14:22:46 +08:00
Aiden Dai
8a9ab560f1 Refine tool call 2024-04-11 20:53:26 +08:00
Aiden Dai
f11a95cc19 Add support of encoded image url 2024-04-10 09:49:48 +08:00
Aiden Dai
81716238ec Add support of encoded image url 2024-04-09 20:43:29 +08:00
Aiden Dai
912c19fcff Fix api path 2024-04-03 20:29:50 +08:00
Aiden Dai
ac20696a8a Add Dockerfile for fargate 2024-04-03 17:07:15 +08:00
Aiden Dai
8a10eb08b6 Add support of Mistral Large 2024-04-03 11:47:07 +08:00
Aiden Dai
02095c030f Add support of Mistral Large 2024-04-03 11:46:10 +08:00
Aiden Dai
268c5ef0f1 Clean up code 2024-04-03 11:20:31 +08:00
Aiden Dai
f1440602ce Add Tool call support 2024-04-03 11:10:19 +08:00
Aiden Dai
e49a579a41 Add multimodal support 2024-04-02 13:10:15 +08:00
Aiden Dai
31ae10a275 Update embedding API 2024-04-02 10:39:55 +08:00
Aiden Dai
beed3b04b7 Update embedding API 2024-04-02 09:30:18 +08:00
Joao Galego
c3b7395028 Added missing input type checking (Cohere Embed); Removed fingerprint from BaseEmbeddingsResponse 2024-03-28 08:05:39 +00:00
Joao Galego
b24a43f6f4 Added support for Cohere Embed and Titan Embeddings models 2024-03-27 17:27:23 +00:00
Aiden Dai
2c2cf10010 Initial commit 2024-03-27 15:24:51 +08:00