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
c8b59aeda7
removed the raw response debug statement
2025-09-05 12:52:01 -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
00c543667d
fixed integration tests and cleaned up logs
2025-09-04 21:49:54 -07:00
Salman Paracha
ee52c608f7
fixed test cases and added more structured logs
2025-09-04 19:28:47 -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
c55979307e
intentionally removing the headers
2025-08-30 23:00:04 -07:00
Salman Paracha
7c4174a821
fixing json parsing errors
2025-08-30 12:52:59 -07:00
Salman Paracha
041a9eda3a
fixed the debug statement that was causing the integration tests for wasm to fail
2025-08-29 18:33:18 -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
77491b4a69
adding some debug logs to help
2025-08-24 14:11:21 -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
d341f4365b
In request path use same format for usage preferences as arch_config ( #533 )
2025-07-21 18:31:19 -07:00
Adil Hafeez
83f4d33434
refactor logging in brightstaff ( #532 )
...
refactor logs, move unnecessary info log statements to debug and start logging latest chat completion message to log
2025-07-17 16:00:04 -07:00
Adil Hafeez
f819ee3507
pass model name in header when a route is selected when using usage preferences ( #531 )
2025-07-17 13:41:58 -07:00
Adil Hafeez
a7fddf30f9
better model names ( #517 )
2025-07-11 16:42:16 -07:00
Adil Hafeez
147908ba7e
make arch-router cluster optional ( #518 )
2025-07-08 00:33:40 -07:00
Adil Hafeez
00dc95e034
Add support for updating model preferences ( #510 )
2025-07-02 14:08:19 -07:00
Salman Paracha
a03aef8b4c
local support for Arch-Router via Ollama ( #509 )
...
* local support for Arch-Router via Ollama
* fixed issue withe non-local yaml config
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-329.local>
2025-06-20 17:32:14 -07:00
Adil Hafeez
7baec20772
release 0.3.2 ( #507 )
2025-06-13 17:02:20 -07:00
Adil Hafeez
aa9d747fa9
add support for gemini ( #505 )
2025-06-11 15:15:00 -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
Adil Hafeez
0d190a6e5c
update code to use new json based system prompt for routing ( #493 )
2025-05-30 17:40:46 -07:00
Adil Hafeez
8d12a9a6e0
add arch provider ( #494 )
2025-05-30 17:12:52 -07:00
Adil Hafeez
176f039bbc
fix model warning and use openwebui for preference based router demo
2025-05-30 12:29:56 -07:00
Adil Hafeez
fffa837a06
separate out currency exchange and preference based routing ( #491 )
2025-05-30 02:14:37 -07:00
Adil Hafeez
470cdf9843
use provider_name as model_id /v1/models api ( #490 )
2025-05-29 11:23:18 -07:00
Adil Hafeez
9c4733590f
add support for openwebui ( #487 )
2025-05-28 19:08:00 -07:00
Adil Hafeez
d29eba4102
trim conversation if it exceed max limit of what router model can handle ( #488 )
2025-05-27 20:28:22 -07:00
Adil Hafeez
99dd900a34
fix panic in brightstaff ( #485 )
...
make router section optional in arch_config
2025-05-23 09:37:25 -07:00
Adil Hafeez
d050dfb85a
When router usage is defined ensure that router model is defined too ( #481 )
2025-05-23 08:46:12 -07:00
Adil Hafeez
218e9c540d
Add support for json based content types in Message ( #480 )
2025-05-23 00:51:53 -07:00
Adil Hafeez
f5e77bbe65
add support for claude and add first class support for groq and deepseek ( #479 )
2025-05-22 22:55:46 -07:00
Adil Hafeez
27c0f2fdce
Introduce brightstaff a new terminal service for llm routing ( #477 )
2025-05-19 09:59:22 -07:00
Shuguang Chen
7d4b261a68
Integrate Arch-Function-Chat ( #449 )
2025-04-15 14:39:12 -07:00
Salman Paracha
f31aa59fac
fixed issue with groq LLMs that require the openai in the /v1/chat/co… ( #460 )
...
* fixed issue with groq LLMs that require the openai in the /v1/chat/completions path. My first change
* updated the GH actions with keys for Groq
* adding missing groq API keys
* add llama-3.2-3b-preview to the model based on addin groq to the demo
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2025-04-13 14:00:16 -07:00
