mirror of
https://github.com/katanemo/plano.git
synced 2026-05-12 01:02:56 +02:00
removing model_server python module to brightstaff (function calling) (#615)
* adding function_calling functionality via rust * fixed rendered YAML file * removed model_server from envoy.template and forwarding traffic to bright_staff * fixed bugs in function_calling.rs that were breaking tests. All good now * updating e2e test to clean up disk usage * removing Arch* models to be used as a default model if one is not specified * if the user sets arch-function base_url we should honor it * fixing demos as we needed to pin to a particular version of huggingface_hub else the chatbot ui wouldn't build * adding a constant for Arch-Function model name * fixing some edge cases with calls made to Arch-Function * fixed JSON parsing issues in function_calling.rs * fixed bug where the raw response from Arch-Function was re-encoded * removed debug from supervisord.conf * commenting out disk cleanup * adding back disk space --------- Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local> Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
This commit is contained in:
parent
126b029345
commit
88c2bd1851
40 changed files with 2517 additions and 1356 deletions
|
|
@ -7,7 +7,7 @@ pub const ARCH_FC_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
|
|||
pub const DEFAULT_TARGET_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
|
||||
pub const API_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
|
||||
pub const MODEL_SERVER_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
|
||||
pub const MODEL_SERVER_NAME: &str = "model_server";
|
||||
pub const MODEL_SERVER_NAME: &str = "bright_staff";
|
||||
pub const ARCH_ROUTING_HEADER: &str = "x-arch-llm-provider";
|
||||
pub const MESSAGES_KEY: &str = "messages";
|
||||
pub const ARCH_PROVIDER_HINT_HEADER: &str = "x-arch-llm-provider-hint";
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue