Commit graph

362 commits

Author SHA1 Message Date
Adil Hafeez
eb48f3d5bb
use passed in model name in chat completion request (#445) 2025-03-21 15:56:17 -07:00
Salman Paracha
bd8004d1ae
updated docs to reflect agent routing and hand off (#443)
* updated docs to reflect agent routing and hand off

* updated prompt targets based on review

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2025-03-20 13:57:33 -07:00
Adil Hafeez
84cd1df7bf
add preliminary support for llm agents (#432) 2025-03-19 15:21:34 -07:00
Salman Paracha
8d66fefded
Update README.md (#439)
* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md
2025-03-19 14:19:49 -07:00
Salman Paracha
85c8299a2b
Update README.md (#438)
fixed typo
2025-03-19 13:45:35 -07:00
Salman Paracha
852ecf73f2 fixing typos 2025-03-18 22:37:24 -07:00
Salman Paracha
c43513caff
updating README to better describe the problems we are solving (#437)
* updating README to better describe the problems we are solving
* fixing formatting issues

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2025-03-18 22:34:42 -07:00
Adil Hafeez
d2cb1427fb
add hurl tests for currency exchange demo (#435) 2025-03-17 14:21:41 -07:00
Salman Paracha
6072d6ef30
updating the docs to improve usage guide for prompt_targets and function calling (#434)
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2025-03-17 14:07:06 -07:00
Adil Hafeez
5526314b3c
fix ollama demo - add egress endpoint for llm routing (#433) 2025-03-17 11:50:14 -07:00
Salman Paracha
ffb8566c36
updating the network agent to work agin (#425)
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2025-03-08 14:29:11 -08:00
Adil Hafeez
e8dc7f18d3
start using base_url in place of endpoint (#430) 2025-03-05 17:20:04 -08:00
Adil Hafeez
ed3845040e
add demo for deepseek (#426) 2025-03-05 14:08:06 -08:00
Pat Thibodeau
2d357ddd5e
Update discord server invite url (#428) 2025-03-05 13:21:35 -08:00
Adil Hafeez
d8b833fe69
release 0.2.3 (#423) 2025-03-04 14:30:44 -08:00
Adil Hafeez
09c9d3706e
publish docker release images (#422)
* add release docker publish

* more testing

* fix more
2025-03-04 14:16:03 -08:00
Salman Paracha
2e2680c98c
Salanap/java debug ai (#416)
* stashing changes on my local branch

* updated the java demo with debug points and jaeger tracing

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2025-03-04 12:49:34 -08:00
Shuguang Chen
e77fc47225
Handle intent matching better in arch gateway (#391) 2025-03-04 12:49:13 -08:00
Adil Hafeez
10cad4d0b7
add health check endpoint for llm gateway (#420)
* add health check endpoint for llm gateway

* fix rust tests
2025-03-03 13:11:57 -08:00
Sid Golestane
a402fee13b
fix: add --type=container to docker inspect to prevent Podman conflicts (#418)
* fix: add --type=container to docker inspect to prevent Podman conflicts

Adding `--type=container` ensures `docker inspect` targets containers
specifically, preventing conflicts with images in Podman.

* Format Python code using pre-commit hook

---------

Co-authored-by: Sid Golestaneh <sid@golestaneh.com>
2025-02-28 17:03:21 -08:00
Adil Hafeez
ae6b2bef59
Fix compatibility issues with podman system (#415)
- "dokcer inspect" doesn't return State/Status if container is not running
- "docker remove" is not a command supported by podman
- "docker logs" expect -f to be passed before container name
2025-02-20 16:19:48 -08:00
Adil Hafeez
1bbc5d2233
release 0.2.2 (#413) 2025-02-14 20:02:59 -08:00
Adil Hafeez
e40b13be05
Update arch_config and add tests for arch config file (#407) 2025-02-14 19:28:10 -08:00
Adil Hafeez
d0a783cca8
use docker cli to communicate to docker sub system (#412) 2025-02-14 17:46:58 -08:00
Adil Hafeez
2f6c4348fd
update jaeger (#411) 2025-02-14 14:55:41 -08:00
CTran
e7b370cd2f
fix error in function name + new thresholds (#406)
* fix error in function name + new thresholds

* fix

* fix

* remove example

* remove example
2025-02-14 09:57:39 -08:00
Adil Hafeez
4ec03af16e
use archfc hosted on aws (#409) 2025-02-13 11:03:34 -08:00
Salman Paracha
28ee14a75c
updated the spotify bearer authorization README and fixed main README… (#402)
* updated the spotify bearer authorization README and fixed main README links

* minor fixes to SPOTIFY README

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2025-02-10 17:56:28 -08:00
Ashwin Ramaswami
c9fe7a7eba
Fix typo (#401) 2025-02-10 13:55:17 -08:00
Salman Paracha
6ad70d9737
Fixing relative link to the shared chatbotui in the spotify demo, and add references to it in the README (#400) 2025-02-10 11:23:04 -08:00
Adil Hafeez
0ea237fbac
release 0.2.1 (#399) 2025-02-07 19:21:20 -08:00
Adil Hafeez
8de6eacfbd
spotify demo with optimized context window code change (#397) 2025-02-07 19:14:15 -08:00
Salman Paracha
b3c95a6698
refactor demos (#398) 2025-02-07 18:45:42 -08:00
Adil Hafeez
2bd61d628c
add ability to specify custom http headers in api endpoint (#386) 2025-02-06 11:48:09 -08:00
Adil Hafeez
e82f8f216f
Encode parameter values in http path and ... (#395)
* Encode parameter values in http path and ...

- don't send param values in request body in http get request
- send param values in http post request

* rust tests

* refactor code

* add tests
2025-02-06 11:00:47 -08:00
Adil Hafeez
a62f906432
remove unused cargo.lock files (#396) 2025-02-05 20:25:41 -08:00
Adil Hafeez
afa2142d93
run rust tests for all crates upon commit (#393) 2025-02-05 18:57:01 -08:00
Adil Hafeez
fa089ef32d
Publish both arm64 and amd64 in docker on main (#392) 2025-02-04 15:04:09 -08:00
Adil Hafeez
962727f244
Infer port from protocol if port is not specified and add ability to override hostname in clusters def (#389) 2025-02-03 14:51:59 -08:00
obinnascale3
25692bbbfc
Add Langtrace as a supported observability tool (#376)
* add langtrace as a tracing tool

* add setup step for Arch installation

---------

Co-authored-by: Obinna Okafor <obinna.okafor01@gmail.com>
2025-01-31 11:16:30 -08:00
Adil Hafeez
39266b5084
log improvements and some code refactor (#379) 2025-01-31 10:37:53 -08:00
Salman Paracha
e79d16ec81
Updated README layout (#387)
* Updated README layout

* minor fixes

* minor fixes

* minor fixes

* minor fixes

* minor fixes

* minor clean up

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2025-01-30 17:36:11 -08:00
Adil Hafeez
a7feb6bffb
fix llm_provider format (#385) 2025-01-24 20:35:56 -08:00
Adil Hafeez
7830f4b431
release 0.2.0 (#384)
* release 0.2.0

* update versions
2025-01-24 17:31:48 -08:00
Adil Hafeez
38f7691163
add support for custom llm with ssl support (#380)
* add support for custom llm with ssl support

Add support for using custom llm that are served through https protocol.

* add instructions on how to add custom inference endpoint

* fix formatting

* add more details

* Apply suggestions from code review

Co-authored-by: Salman Paracha <salman.paracha@gmail.com>

* Apply suggestions from code review

* fix precommit

---------

Co-authored-by: Salman Paracha <salman.paracha@gmail.com>
2025-01-24 17:14:24 -08:00
Adil Hafeez
2c67fa3bc0
Fix llm_routing provider element (#382)
* Fix llm_routing provider element

We replaced provider with provider_interface to make it more clear to developers about provider api/backend being used. During that upgrade we removed support for mistral in provider to encourage developers to start using provider_interface. But this demo was not updated to use provider_interface as it was using mistral. This code change fixes it by replacing provider with provider_interface.

Signed-off-by: Adil Hafeez <adil.hafeez@gmail.com>

* fix the path

* move

* add more details

* fix

* Apply suggestions from code review

* fix

* fix

---------

Signed-off-by: Adil Hafeez <adil.hafeez@gmail.com>
2025-01-24 16:34:11 -08:00
Guy Stone
84af476c75
Add run_demo.sh for llm_routing demo (#381)
* Create run_demo.sh for llm_routing demo

* Update run_demo.sh
2025-01-24 14:41:51 -08:00
Salman Paracha
1e75c1c5e0 updating README 2025-01-23 11:31:10 -08:00
Salman Paracha
1d9bfcb7db
Update README.md 2025-01-23 11:26:21 -08:00
Salman Paracha
f9bed5d75c
Update README.md 2025-01-23 11:25:46 -08:00