v0.9.6

What's Changed

• Automated Build for Parallel Interface by @paulguerrie in #168
• Deprecate TRT Support by @paulguerrie in #169
• Better API Key Docs and Error Handling by @paulguerrie in #171
• Add true implementation for AL configuration getter by @PawelPeczek-Roboflow in #173
• Bug Fix for Numpy Inputs by @paulguerrie in #172
• features/sv-from-roboflow-no-need-class-list-args by @ShingoMatsuura in #149
• Add development documentation of Active Learning by @PawelPeczek-Roboflow in #167
• Refactor inference methods to use make_response directly by @SkalskiP in #147
• Updated HTTP Quickstart by @paulguerrie in #176
• Peter/cogvlm by @probicheaux in #175
• Error Handling for Onnx Session Creation by @paulguerrie in #177
• Slim Docker Images by @paulguerrie in #178
• Rename cog to cogvlm by @paulguerrie in #182
• Wheel and Setuptools Upgrade by @paulguerrie in #184
• Finalize keypoint detection by @SolomonLake in #174
• Parallel Entrypoint Cleanup by @probicheaux in #179
• Peter/orjson by @probicheaux in #166
• Remove Legacy Cache Path by @paulguerrie in #185
• Multi-Stage Builds by @paulguerrie in #186
• Revert "Peter/orjson" by @PawelPeczek-Roboflow in #190
• Accept numpy image in batch as base64 encoded string by @sberan in #187
• Improve missing api key error handling by @PawelPeczek-Roboflow in #188

Highlights

CogVLM

Inference server users can now run CogVLM for a fully self hosted, multimodal LLM. See the example here.

Slim Docker Images

For use cases that do not need Core Model functionality (e.g. CLIP), there are -slim docker images available which include fewer dependancies and are much smaller.

• roboflow/roboflow-inference-server-cpu-slim
• roboflow/roboflow-inference-server-gpu-slim

Breaking Changes

Infer API Update

The infer() method of Roboflow models now returns an InferenceResponse object instead of raw model output. This means that using models in application logic should feel similar to using models via the HTTP interface. In practice, programs that used the following pattern

...
model = get_roboflow_model(...)
results = model.infer(...)
results = model.make_response(...)
...

should be updated to

...
model = get_roboflow_model(...)
results = model.infer(...)
...

New Contributors

• @ShingoMatsuura made their first contribution in #149

Full Changelog: v0.9.5...v0.9.6