- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent
Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:
- The inference API should be a routing layer over inference providers,
routed using the "model" key
- The memory banks API is another instance where various memory bank
types will be provided by independent providers (e.g., a vector store
is served by Chroma while a keyvalue memory can be served by Redis or
PGVector)
This commit introduces a generalized routing layer for this purpose.
* [1/n] migrate inference/chat_completion
* migrate inference/completion
* inference/completion
* inference regenerate openapi spec
* safety api
* migrate agentic system
* migrate apis without implementations
* re-generate openapi spec
* remove hack from openapi generator
* fix inference
* fix inference
* openapi generator rerun
* Simplified Telemetry API and tying it to logger (#57)
* Simplified Telemetry API and tying it to logger
* small update which adds a METRIC type
* move span events one level down into structured log events
---------
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
* fix api to work with openapi generator
* fix agentic calling inference
* together adapter inference
* update inference adapters
---------
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
* support data: in URL for memory. Add ootb support for pdfs
* moved utility to common and updated data_url parsing logic
---------
Co-authored-by: Hardik Shah <hjshah@fb.com>
* Use huggingface_hub inference client for TGI inference
* Update the default value for TGI URL
* Use InferenceClient.text_generation for TGI inference
* Fixes post-review and split TGI adapter into local and Inference Endpoints ones
* Update CLI reference and add typing
* Rename TGI Adapter class
* Use HfApi to get the namespace when not provide in the hf endpoint name
* Remove unecessary method argument
* Improve TGI adapter initialization condition
* Move helper into impl file + fix merging conflicts
* Simplified Telemetry API and tying it to logger
* small update which adds a METRIC type
* move span events one level down into structured log events
---------
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
* Query generators for rag query
* use agent.inference_api instead of passing host/port again
* drop classes for functions
---------
Co-authored-by: Hardik Shah <hjshah@fb.com>
* TGI adapter and some refactoring of other inference adapters
* Use the lower-level `generate_stream()` method for correct tool calling
---------
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
