You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 73fb5e8
Browse filesBrowse the repository at this point in the historyBrowse files
feat: add Databricks AI Gateway as LLM provider (#649)
Implements Databricks serving endpoints support with PAT auth,
workspace URL resolution, and OpenAI-compatible request handling.
- Add databricks ProviderID to schema
- Create auth plugin with PAT parsing and host validation
- Add custom loader with env var fallback (DATABRICKS_HOST + DATABRICKS_TOKEN)
- Register 11 foundation models (Llama, Claude, GPT, Gemini, DBRX, Mixtral)
- Add 24 unit tests for host validation, PAT parsing, body transforms
- E2E tests included (skipped without credentials)
Closes#602
Co-authored-by: anandgupta42 <[email protected]>
"Enter your credentials as: <workspace-host>::<PAT-token>\n e.g. myworkspace.cloud.databricks.com::dapi1234567890abcdef\n Create a PAT in Databricks: Settings → Developer → Access Tokens → Generate New Token",
107
+
method: "code"asconst,
108
+
callback: async(code: string)=>{
109
+
constparsed=parseDatabricksPAT(code)
110
+
if(!parsed)return{type: "failed"asconst}
111
+
return{
112
+
type: "success"asconst,
113
+
access: parsed.token,
114
+
refresh: "",
115
+
// Databricks PATs can be configured with custom TTLs; use 90-day default
0 commit comments