Commit graph

23 commits

Author SHA1 Message Date
Salman Paracha
06c71c1392 moved away from string literals to consts 2025-09-06 10:47:05 -07:00
Salman Paracha
e8881c7b8a fixed the dup cloning issue and cleaned up the ProviderRequestType enum and traits 2025-09-05 21:18:55 -07:00
Salman Paracha
2895a07088 cleaned up logs and fixed issue with connectivity for llm gateway in weather forecast demo 2025-09-05 09:09:17 -07:00
Salman Paracha
ecf453ed70 /v1/messages works with transformations to and from /v1/chat/completions 2025-09-04 15:13:53 -07:00
Salman Paracha
2813a8cfa5 fixing non-streaming responses to tranform correctly 2025-09-02 17:42:02 -07:00
Salman Paracha
d4dfbe600f making sure that we convert the raw bytes to the correct provider type upstream 2025-09-02 16:19:45 -07:00
Salman Paracha
7c4174a821 fixing json parsing errors 2025-08-30 12:52:59 -07:00
Salman Paracha
0a0d2c95a3 the serialized bytes length must be set in the response side 2025-08-29 18:18:32 -07:00
Salman Paracha
e7238fb7fd updated the stream_context to update response bytes 2025-08-28 22:55:12 -07:00
Salman Paracha
9f6d2464f6 fixed issues with non-streaming responses 2025-08-24 18:52:48 -07:00
Salman Paracha
0b41496c45 fixed serialization issues with enums on response 2025-08-24 13:12:15 -07:00
Salman Paracha
2fa983d50d fixed doc tests 2025-08-23 16:48:06 -07:00
Salman Paracha
7345657612 fixed bugs for integration tests 2025-08-23 16:37:52 -07:00
Salman Paracha
9f3a6f71a3 updated tests and added necessary response transformations for Anthropics' message response object 2025-08-22 16:06:48 -07:00
Salman Paracha
e73a9eb61c transformations are working. Now need to add some tests next 2025-08-22 14:36:46 -07:00
Salman Paracha
0aa9243093 pushing draft PR 2025-08-21 22:24:07 -07:00
Salman Paracha
89ab51697a
updating the implementation of /v1/chat/completions to use the generi… (#548)
* updating the implementation of /v1/chat/completions to use the generic provider interfaces

* saving changes, although we will need a small re-factor after this as well

* more refactoring changes, getting close

* more refactoring changes to avoid unecessary re-direction and duplication

* more clean up

* more refactoring

* more refactoring to clean code and make stream_context.rs work

* removing unecessary trait implemenations

* some more clean-up

* fixed bugs

* fixing test cases, and making sure all references to the ChatCOmpletions* objects point to the new types

* refactored changes to support enum dispatch

* removed the dependency on try_streaming_from_bytes into a try_from trait implementation

* updated readme based on new usage

* updated code based on code review comments

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-2.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-4.local>
2025-08-20 12:55:29 -07:00
Salman Paracha
93ff4d7b1f
pushing new apis module for hermes (#547) 2025-08-07 12:42:09 -07:00
Adil Hafeez
04c7e5a175
bug fix - allow image content to pass through (#539)
fixes https://github.com/katanemo/archgw/issues/535
2025-07-25 01:22:06 -07:00
Adil Hafeez
00dc95e034
Add support for updating model preferences (#510) 2025-07-02 14:08:19 -07:00
Adil Hafeez
e734b76086
fix build break 2025-06-10 13:07:35 -07:00
Adil Hafeez
fb34dbdf6c
remove unnecessary rust files 2025-06-10 12:54:31 -07:00
Adil Hafeez
6c53510f49
Introduce hermesllm library to handle llm message translation (#501) 2025-06-10 12:53:27 -07:00