v0.1.3

v0.1.3 Release

Here are some key changes that are coming as part of this release.

Build and Test Agents

Streamlined the initial development experience

• Added support for llama stack run --image-type venv
• Enhanced vector store options with new sqlite-vec provider and improved Qdrant integration
• vLLM improvements for tool calling and logprobs
• Better handling of sporadic code_interpreter tool calls

Agent Evals

Better benchmarking and Agent performance assessment

• Renamed eval API /eval-task to /benchmarks
• Improved documentation and notebooks for RAG and evals

Deploy and Monitoring of Agents

Improved production readiness

• Added usage metrics collection for chat completions
• CLI improvements for provider information
• Improved error handling and system reliability
• Better model endpoint handling and accessibility
• Improved signal handling on distro server

Better Engineering

Infrastructure and code quality improvements

• Faster text-based chat completion tests
• Improved testing for non-streaming agent apis
• Standardized import formatting with ruff linter
• Added conventional commits standard
• Fixed documentation parsing issues

What's Changed

• Getting started notebook update by @jeffxtang in #936
• docs: update index.md for 0.1.2 by @raghotham in #1013
• test: Make text-based chat completion tests run 10x faster by @terrytangyuan in #1016
• chore: Updated requirements.txt by @cheesecake100201 in #1017
• test: Use JSON tool prompt format for remote::vllm provider by @terrytangyuan in #1019
• docs: Render check marks correctly on PyPI by @terrytangyuan in #1024
• docs: update rag.md example code to prevent errors by @MichaelClifford in #1009
• build: update uv lock to sync package versions by @leseb in #1026
• fix: Gaps in doc codegen by @ellistarn in #1035
• fix: Readthedocs cannot parse comments, resulting in docs bugs by @ellistarn in #1033
• fix: a bad newline in ollama docs by @ellistarn in #1036
• fix: Update Qdrant support post-refactor by @jwm4 in #1022
• test: replace blocked image URLs with GitHub-hosted by @leseb in #1025
• fix: Added missing tool_config arg in SambaNova chat_completion() by @terrytangyuan in #1042
• docs: Updating wording and nits in the README.md by @kelbrown20 in #992
• docs: remove changelog mention from PR template by @leseb in #1049
• docs: reflect actual number of spaces for indent by @booxter in #1052
• fix: agent config validation by @ehhuang in #1053
• feat: add MetricResponseMixin to chat completion response types by @dineshyv in #1050
• feat: make telemetry attributes be dict[str,PrimitiveType] by @dineshyv in #1055
• fix: filter out remote::sample providers when listing by @booxter in #1057
• feat: Support tool calling for non-streaming chat completion in remote vLLM provider by @terrytangyuan in #1034
• perf: ensure ToolCall in ChatCompletionResponse is subset of ChatCompletionRequest.tools by @yanxi0830 in #1041
• chore: update return type to Optional[str] by @leseb in #982
• feat: Support tool calling for streaming chat completion in remote vLLM provider by @terrytangyuan in #1063
• fix: show proper help text by @cdoern in #1065
• feat: add support for running in a venv by @cdoern in #1018
• feat: Adding sqlite-vec as a vectordb by @franciscojavierarceo in #1040
• feat: support listing all for llama stack list-providers by @booxter in #1056
• docs: Mention convential commits format in CONTRIBUTING.md by @bbrowning in #1075
• fix: logprobs support in remote-vllm provider by @bbrowning in #1074
• fix: improve signal handling and update dependencies by @leseb in #1044
• style: update model id in model list title by @reidliu41 in #1072
• fix: make backslash work in GET /models/{model_id:path} by @yanxi0830 in #1068
• chore: Link to Groq docs in the warning message for preview model by @terrytangyuan in #1060
• fix: remove :path in agents by @yanxi0830 in #1077
• build: format codebase imports using ruff linter by @leseb in #1028
• chore: Consistent naming for VectorIO providers by @terrytangyuan in #1023
• test: Enable logprobs top_k tests for remote::vllm by @terrytangyuan in #1080
• docs: Fix url to the llama-stack-spec yaml/html files by @vishnoianil in #1081
• fix: Update VectorIO config classes in registry by @terrytangyuan in #1079
• test: Add qdrant to provider tests by @jwm4 in #1039
• test: add test for Agent.create_turn non-streaming response by @ehhuang in #1078
• fix!: update eval-tasks -> benchmarks by @yanxi0830 in #1032
• fix: openapi for eval-task by @yanxi0830 in #1085
• fix: regex pattern matching to support :path suffix in the routes by @hardikjshah in #1089
• fix: disable sqlite-vec test by @yanxi0830 in #1090
• fix: add the missed help description info by @reidliu41 in #1096
• fix: Update QdrantConfig to QdrantVectorIOConfig by @bbrowning in #1104
• docs: Add region parameter to Bedrock provider by @raghotham in #1103
• build: configure ruff from pyproject.toml by @leseb in #1100
• chore: move all Llama Stack types from llama-models to llama-stack by @ashwinb in #1098
• fix: enable_session_persistence in AgentConfig should be optional by @terrytangyuan in #1012
• fix: improve stack build on venv by @leseb in #980
• fix: remove the empty line by @reidliu41 in #1097

New Contributors

• @MichaelClifford made their first contribution in #1009
• @ellistarn made their first contribution in #1035
• @kelbrown20 made their first contribution in #992
• @franciscojavierarceo made their first contribution in #1040
• @bbrowning made their first contribution in #1075
• @reidliu41 made their first contribution in #1072
• @vishnoianil made their first contribution in #1081

Full Changelog: v0.1.2...v0.1.3