Commit graph

5 commits

Author SHA1 Message Date
yujonglee
bfcb9a028f
refactor(rust): update OCR route orchestration (#47216)
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-19 09:03:44 -07:00
yujonglee
04a95f60c1
feat(rust): type the Vertex AI connection params and where Python reads them (#45641)
VertexParams in auth-types holds the vertex_* fields of CredentialLiteLLMParams
in both spellings, with one ParamSpec per setting: the wire names, the litellm
module global VertexBase.get_vertex_ai_* consults, and the environment names.
A credential deserializes from text or the JSON object a config spells, an
empty object counts as absent, and both credential fields are redacted in
Debug. auth-gcp is split so lib.rs is the entrypoint (config, auth,
constants), its lookups resolve through the specs, secret_names() derives
from them, and get_vertex_ai_project_from_credentials reads a service
account's project_id for hosts that need it before a token exchange. The OCR
host folds the module globals in by spec at projection, so OcrSettings no
longer carries vertex_project and vertex_location.
2026-10-09 16:29:44 -07:00
yujonglee
0410abea8b
feat(rust): type the AWS connection params and where Python reads them (#45610)
AwsParams in auth-types holds the aws_* fields of CredentialLiteLLMParams
with one ParamSpec per field: its wire name and the environment names it
falls back to. fields() and secret_names() derive from the specs, the AWS
helpers take the struct instead of a map, aws_auth_config and the region
resolution read through the specs, and a missing region is
AwsParams::REGION.missing("AWS"), whose message is rendered from the spec.
Bedrock Converse, Bedrock transcription, Textract OCR and the Bedrock
Messages config build the struct at their one untyped boundary.
2026-10-09 16:29:44 -07:00
devin-ai-integration[bot]
878ba39e7c
refactor(rust): extract inference-testing crate (#44873)
Move the shared test helpers out of litellm-inference's test-support
feature into a publish = false litellm-inference-testing crate used only
as a dev dependency by the format crates.

Also drop the dead src/constants.rs (OPENAI_DEFAULT_API_BASE had no
users) and declare the litellm-http/litellm-llms test-support features
on the crates that actually use them instead of relying on feature
unification through litellm-inference's dev-dependencies.

Co-authored-by: Yujong Lee <yujong@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-06 16:33:06 +00:00
devin-ai-integration[bot]
ae35c9d775
refactor(rust): extract inference-ocr crate (#44832)
Co-authored-by: Yujong Lee <yujong@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-06 07:17:26 -07:00