mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-02 08:44:44 +00:00
Merge branch 'main' into install-script-podman-fix
This commit is contained in:
Alexey Rybak
GitHub
commit
7d7b919d85
51 changed files with 454 additions and 417 deletions
|
|
@ -15,6 +15,18 @@ repos:
|
|||
args: ['--maxkb=1000']
|
||||
- id: end-of-file-fixer
|
||||
exclude: '^(.*\.svg)$'
|
||||
- id: no-commit-to-branch
|
||||
- id: check-yaml
|
||||
args: ["--unsafe"]
|
||||
- id: detect-private-key
|
||||
- id: requirements-txt-fixer
|
||||
- id: mixed-line-ending
|
||||
args: [--fix=lf] # Forces to replace line ending by LF (line feed)
|
||||
- id: check-executables-have-shebangs
|
||||
- id: check-json
|
||||
- id: check-shebang-scripts-are-executable
|
||||
- id: check-symlinks
|
||||
- id: check-toml
|
||||
|
||||
- repo: https://github.com/Lucas-C/pre-commit-hooks
|
||||
rev: v1.5.4
|
||||
|
|
|
|||
562
CHANGELOG.md
562
CHANGELOG.md
|
|
@ -38,10 +38,10 @@ Published on: 2025-04-05T23:13:00Z
|
|||
# v0.2.0
|
||||
Published on: 2025-04-05T19:04:29Z
|
||||
|
||||
## Llama 4 Support
|
||||
|
||||
Checkout more at https://www.llama.com
|
||||
|
||||
## Llama 4 Support
|
||||
|
||||
Checkout more at https://www.llama.com
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
|
@ -49,58 +49,58 @@ Checkout more at https://www.llama.com
|
|||
# v0.1.9
|
||||
Published on: 2025-03-29T00:52:23Z
|
||||
|
||||
### Build and Test Agents
|
||||
* Agents: Entire document context with attachments
|
||||
* RAG: Documentation with sqlite-vec faiss comparison
|
||||
* Getting started: Fixes to getting started notebook.
|
||||
|
||||
### Agent Evals and Model Customization
|
||||
* (**New**) Post-training: Add nemo customizer
|
||||
|
||||
### Better Engineering
|
||||
* Moved sqlite-vec to non-blocking calls
|
||||
* Don't return a payload on file delete
|
||||
|
||||
|
||||
### Build and Test Agents
|
||||
* Agents: Entire document context with attachments
|
||||
* RAG: Documentation with sqlite-vec faiss comparison
|
||||
* Getting started: Fixes to getting started notebook.
|
||||
|
||||
### Agent Evals and Model Customization
|
||||
* (**New**) Post-training: Add nemo customizer
|
||||
|
||||
### Better Engineering
|
||||
* Moved sqlite-vec to non-blocking calls
|
||||
* Don't return a payload on file delete
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
# v0.1.8
|
||||
Published on: 2025-03-24T01:28:50Z
|
||||
|
||||
# v0.1.8 Release Notes
|
||||
|
||||
### Build and Test Agents
|
||||
* Safety: Integrated NVIDIA as a safety provider.
|
||||
* VectorDB: Added Qdrant as an inline provider.
|
||||
* Agents: Added support for multiple tool groups in agents.
|
||||
* Agents: Simplified imports for Agents in client package
|
||||
|
||||
|
||||
### Agent Evals and Model Customization
|
||||
* Introduced DocVQA and IfEval benchmarks.
|
||||
|
||||
### Deploying and Monitoring Agents
|
||||
* Introduced a Containerfile and image workflow for the Playground.
|
||||
* Implemented support for Bearer (API Key) authentication.
|
||||
* Added attribute-based access control for resources.
|
||||
* Fixes on docker deployments: use --pull always and standardized the default port to 8321
|
||||
* Deprecated: /v1/inspect/providers use /v1/providers/ instead
|
||||
|
||||
### Better Engineering
|
||||
* Consolidated scripts under the ./scripts directory.
|
||||
* Addressed mypy violations in various modules.
|
||||
* Added Dependabot scans for Python dependencies.
|
||||
* Implemented a scheduled workflow to update the changelog automatically.
|
||||
* Enforced concurrency to reduce CI loads.
|
||||
|
||||
|
||||
### New Contributors
|
||||
* @cmodi-meta made their first contribution in https://github.com/meta-llama/llama-stack/pull/1650
|
||||
* @jeffmaury made their first contribution in https://github.com/meta-llama/llama-stack/pull/1671
|
||||
* @derekhiggins made their first contribution in https://github.com/meta-llama/llama-stack/pull/1698
|
||||
* @Bobbins228 made their first contribution in https://github.com/meta-llama/llama-stack/pull/1745
|
||||
|
||||
# v0.1.8 Release Notes
|
||||
|
||||
### Build and Test Agents
|
||||
* Safety: Integrated NVIDIA as a safety provider.
|
||||
* VectorDB: Added Qdrant as an inline provider.
|
||||
* Agents: Added support for multiple tool groups in agents.
|
||||
* Agents: Simplified imports for Agents in client package
|
||||
|
||||
|
||||
### Agent Evals and Model Customization
|
||||
* Introduced DocVQA and IfEval benchmarks.
|
||||
|
||||
### Deploying and Monitoring Agents
|
||||
* Introduced a Containerfile and image workflow for the Playground.
|
||||
* Implemented support for Bearer (API Key) authentication.
|
||||
* Added attribute-based access control for resources.
|
||||
* Fixes on docker deployments: use --pull always and standardized the default port to 8321
|
||||
* Deprecated: /v1/inspect/providers use /v1/providers/ instead
|
||||
|
||||
### Better Engineering
|
||||
* Consolidated scripts under the ./scripts directory.
|
||||
* Addressed mypy violations in various modules.
|
||||
* Added Dependabot scans for Python dependencies.
|
||||
* Implemented a scheduled workflow to update the changelog automatically.
|
||||
* Enforced concurrency to reduce CI loads.
|
||||
|
||||
|
||||
### New Contributors
|
||||
* @cmodi-meta made their first contribution in https://github.com/meta-llama/llama-stack/pull/1650
|
||||
* @jeffmaury made their first contribution in https://github.com/meta-llama/llama-stack/pull/1671
|
||||
* @derekhiggins made their first contribution in https://github.com/meta-llama/llama-stack/pull/1698
|
||||
* @Bobbins228 made their first contribution in https://github.com/meta-llama/llama-stack/pull/1745
|
||||
|
||||
**Full Changelog**: https://github.com/meta-llama/llama-stack/compare/v0.1.7...v0.1.8
|
||||
|
||||
---
|
||||
|
|
@ -108,73 +108,73 @@ Published on: 2025-03-24T01:28:50Z
|
|||
# v0.1.7
|
||||
Published on: 2025-03-14T22:30:51Z
|
||||
|
||||
## 0.1.7 Release Notes
|
||||
|
||||
### Build and Test Agents
|
||||
* Inference: ImageType is now refactored to LlamaStackImageType
|
||||
* Inference: Added tests to measure TTFT
|
||||
* Inference: Bring back usage metrics
|
||||
* Agents: Added endpoint for get agent, list agents and list sessions
|
||||
* Agents: Automated conversion of type hints in client tool for lite llm format
|
||||
* Agents: Deprecated ToolResponseMessage in agent.resume API
|
||||
* Added Provider API for listing and inspecting provider info
|
||||
|
||||
### Agent Evals and Model Customization
|
||||
* Eval: Added new eval benchmarks Math 500 and BFCL v3
|
||||
* Deploy and Monitoring of Agents
|
||||
* Telemetry: Fix tracing to work across coroutines
|
||||
|
||||
### Better Engineering
|
||||
* Display code coverage for unit tests
|
||||
* Updated call sites (inference, tool calls, agents) to move to async non blocking calls
|
||||
* Unit tests also run on Python 3.11, 3.12, and 3.13
|
||||
* Added ollama inference to Integration tests CI
|
||||
* Improved documentation across examples, testing, CLI, updated providers table )
|
||||
|
||||
|
||||
|
||||
## 0.1.7 Release Notes
|
||||
|
||||
### Build and Test Agents
|
||||
* Inference: ImageType is now refactored to LlamaStackImageType
|
||||
* Inference: Added tests to measure TTFT
|
||||
* Inference: Bring back usage metrics
|
||||
* Agents: Added endpoint for get agent, list agents and list sessions
|
||||
* Agents: Automated conversion of type hints in client tool for lite llm format
|
||||
* Agents: Deprecated ToolResponseMessage in agent.resume API
|
||||
* Added Provider API for listing and inspecting provider info
|
||||
|
||||
### Agent Evals and Model Customization
|
||||
* Eval: Added new eval benchmarks Math 500 and BFCL v3
|
||||
* Deploy and Monitoring of Agents
|
||||
* Telemetry: Fix tracing to work across coroutines
|
||||
|
||||
### Better Engineering
|
||||
* Display code coverage for unit tests
|
||||
* Updated call sites (inference, tool calls, agents) to move to async non blocking calls
|
||||
* Unit tests also run on Python 3.11, 3.12, and 3.13
|
||||
* Added ollama inference to Integration tests CI
|
||||
* Improved documentation across examples, testing, CLI, updated providers table )
|
||||
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
# v0.1.6
|
||||
Published on: 2025-03-08T04:35:08Z
|
||||
|
||||
## 0.1.6 Release Notes
|
||||
|
||||
### Build and Test Agents
|
||||
* Inference: Fixed support for inline vllm provider
|
||||
* (**New**) Agent: Build & Monitor Agent Workflows with Llama Stack + Anthropic's Best Practice [Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/notebooks/Llama_Stack_Agent_Workflows.ipynb)
|
||||
* (**New**) Agent: Revamped agent [documentation](https://llama-stack.readthedocs.io/en/latest/building_applications/agent.html) with more details and examples
|
||||
* Agent: Unify tools and Python SDK Agents API
|
||||
* Agent: AsyncAgent Python SDK wrapper supporting async client tool calls
|
||||
* Agent: Support python functions without @client_tool decorator as client tools
|
||||
* Agent: deprecation for allow_resume_turn flag, and remove need to specify tool_prompt_format
|
||||
* VectorIO: MilvusDB support added
|
||||
|
||||
### Agent Evals and Model Customization
|
||||
* (**New**) Agent: Llama Stack RAG Lifecycle [Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/notebooks/Llama_Stack_RAG_Lifecycle.ipynb)
|
||||
* Eval: Documentation for eval, scoring, adding new benchmarks
|
||||
* Eval: Distribution template to run benchmarks on llama & non-llama models
|
||||
* Eval: Ability to register new custom LLM-as-judge scoring functions
|
||||
* (**New**) Looking for contributors for open benchmarks. See [documentation](https://llama-stack.readthedocs.io/en/latest/references/evals_reference/index.html#open-benchmark-contributing-guide) for details.
|
||||
|
||||
### Deploy and Monitoring of Agents
|
||||
* Better support for different log levels across all components for better monitoring
|
||||
|
||||
### Better Engineering
|
||||
* Enhance OpenAPI spec to include Error types across all APIs
|
||||
* Moved all tests to /tests and created unit tests to run on each PR
|
||||
* Removed all dependencies on llama-models repo
|
||||
|
||||
## 0.1.6 Release Notes
|
||||
|
||||
### Build and Test Agents
|
||||
* Inference: Fixed support for inline vllm provider
|
||||
* (**New**) Agent: Build & Monitor Agent Workflows with Llama Stack + Anthropic's Best Practice [Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/notebooks/Llama_Stack_Agent_Workflows.ipynb)
|
||||
* (**New**) Agent: Revamped agent [documentation](https://llama-stack.readthedocs.io/en/latest/building_applications/agent.html) with more details and examples
|
||||
* Agent: Unify tools and Python SDK Agents API
|
||||
* Agent: AsyncAgent Python SDK wrapper supporting async client tool calls
|
||||
* Agent: Support python functions without @client_tool decorator as client tools
|
||||
* Agent: deprecation for allow_resume_turn flag, and remove need to specify tool_prompt_format
|
||||
* VectorIO: MilvusDB support added
|
||||
|
||||
### Agent Evals and Model Customization
|
||||
* (**New**) Agent: Llama Stack RAG Lifecycle [Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/notebooks/Llama_Stack_RAG_Lifecycle.ipynb)
|
||||
* Eval: Documentation for eval, scoring, adding new benchmarks
|
||||
* Eval: Distribution template to run benchmarks on llama & non-llama models
|
||||
* Eval: Ability to register new custom LLM-as-judge scoring functions
|
||||
* (**New**) Looking for contributors for open benchmarks. See [documentation](https://llama-stack.readthedocs.io/en/latest/references/evals_reference/index.html#open-benchmark-contributing-guide) for details.
|
||||
|
||||
### Deploy and Monitoring of Agents
|
||||
* Better support for different log levels across all components for better monitoring
|
||||
|
||||
### Better Engineering
|
||||
* Enhance OpenAPI spec to include Error types across all APIs
|
||||
* Moved all tests to /tests and created unit tests to run on each PR
|
||||
* Removed all dependencies on llama-models repo
|
||||
|
||||
|
||||
---
|
||||
|
||||
# v0.1.5.1
|
||||
Published on: 2025-02-28T22:37:44Z
|
||||
|
||||
## 0.1.5.1 Release Notes
|
||||
* Fixes for security risk in https://github.com/meta-llama/llama-stack/pull/1327 and https://github.com/meta-llama/llama-stack/pull/1328
|
||||
|
||||
## 0.1.5.1 Release Notes
|
||||
* Fixes for security risk in https://github.com/meta-llama/llama-stack/pull/1327 and https://github.com/meta-llama/llama-stack/pull/1328
|
||||
|
||||
**Full Changelog**: https://github.com/meta-llama/llama-stack/compare/v0.1.5...v0.1.5.1
|
||||
|
||||
---
|
||||
|
|
@ -182,176 +182,176 @@ Published on: 2025-02-28T22:37:44Z
|
|||
# v0.1.5
|
||||
Published on: 2025-02-28T18:14:01Z
|
||||
|
||||
## 0.1.5 Release Notes
|
||||
### Build Agents
|
||||
* Inference: Support more non-llama models (openai, anthropic, gemini)
|
||||
* Inference: Can use the provider's model name in addition to the HF alias
|
||||
* Inference: Fixed issues with calling tools that weren't specified in the prompt
|
||||
* RAG: Improved system prompt for RAG and no more need for hard-coded rag-tool calling
|
||||
* Embeddings: Added support for Nemo retriever embedding models
|
||||
* Tools: Added support for MCP tools in Ollama Distribution
|
||||
* Distributions: Added new Groq distribution
|
||||
|
||||
### Customize Models
|
||||
* Save post-trained checkpoint in SafeTensor format to allow Ollama inference provider to use the post-trained model
|
||||
|
||||
### Monitor agents
|
||||
* More comprehensive logging of agent steps including client tools
|
||||
* Telemetry inputs/outputs are now structured and queryable
|
||||
* Ability to retrieve agents session, turn, step by ids
|
||||
|
||||
### Better Engineering
|
||||
* Moved executorch Swift code out of this repo into the llama-stack-client-swift repo, similar to kotlin
|
||||
* Move most logging to use logger instead of prints
|
||||
* Completed text /chat-completion and /completion tests
|
||||
|
||||
## 0.1.5 Release Notes
|
||||
### Build Agents
|
||||
* Inference: Support more non-llama models (openai, anthropic, gemini)
|
||||
* Inference: Can use the provider's model name in addition to the HF alias
|
||||
* Inference: Fixed issues with calling tools that weren't specified in the prompt
|
||||
* RAG: Improved system prompt for RAG and no more need for hard-coded rag-tool calling
|
||||
* Embeddings: Added support for Nemo retriever embedding models
|
||||
* Tools: Added support for MCP tools in Ollama Distribution
|
||||
* Distributions: Added new Groq distribution
|
||||
|
||||
### Customize Models
|
||||
* Save post-trained checkpoint in SafeTensor format to allow Ollama inference provider to use the post-trained model
|
||||
|
||||
### Monitor agents
|
||||
* More comprehensive logging of agent steps including client tools
|
||||
* Telemetry inputs/outputs are now structured and queryable
|
||||
* Ability to retrieve agents session, turn, step by ids
|
||||
|
||||
### Better Engineering
|
||||
* Moved executorch Swift code out of this repo into the llama-stack-client-swift repo, similar to kotlin
|
||||
* Move most logging to use logger instead of prints
|
||||
* Completed text /chat-completion and /completion tests
|
||||
|
||||
|
||||
---
|
||||
|
||||
# v0.1.4
|
||||
Published on: 2025-02-25T00:02:43Z
|
||||
|
||||
## v0.1.4 Release Notes
|
||||
Here are the key changes coming as part of this release:
|
||||
|
||||
### Build and Test Agents
|
||||
* Inference: Added support for non-llama models
|
||||
* Inference: Added option to list all downloaded models and remove models
|
||||
* Agent: Introduce new api agents.resume_turn to include client side tool execution in the same turn
|
||||
* Agent: AgentConfig introduces new variable “tool_config” that allows for better tool configuration and system prompt overrides
|
||||
* Agent: Added logging for agent step start and completion times
|
||||
* Agent: Added support for logging for tool execution metadata
|
||||
* Embedding: Updated /inference/embeddings to support asymmetric models, truncation and variable sized outputs
|
||||
* Embedding: Updated embedding models for Ollama, Together, and Fireworks with available defaults
|
||||
* VectorIO: Improved performance of sqlite-vec using chunked writes
|
||||
### Agent Evals and Model Customization
|
||||
* Deprecated api /eval-tasks. Use /eval/benchmark instead
|
||||
* Added CPU training support for TorchTune
|
||||
### Deploy and Monitoring of Agents
|
||||
* Consistent view of client and server tool calls in telemetry
|
||||
### Better Engineering
|
||||
* Made tests more data-driven for consistent evaluation
|
||||
* Fixed documentation links and improved API reference generation
|
||||
* Various small fixes for build scripts and system reliability
|
||||
|
||||
|
||||
## v0.1.4 Release Notes
|
||||
Here are the key changes coming as part of this release:
|
||||
|
||||
### Build and Test Agents
|
||||
* Inference: Added support for non-llama models
|
||||
* Inference: Added option to list all downloaded models and remove models
|
||||
* Agent: Introduce new api agents.resume_turn to include client side tool execution in the same turn
|
||||
* Agent: AgentConfig introduces new variable “tool_config” that allows for better tool configuration and system prompt overrides
|
||||
* Agent: Added logging for agent step start and completion times
|
||||
* Agent: Added support for logging for tool execution metadata
|
||||
* Embedding: Updated /inference/embeddings to support asymmetric models, truncation and variable sized outputs
|
||||
* Embedding: Updated embedding models for Ollama, Together, and Fireworks with available defaults
|
||||
* VectorIO: Improved performance of sqlite-vec using chunked writes
|
||||
### Agent Evals and Model Customization
|
||||
* Deprecated api /eval-tasks. Use /eval/benchmark instead
|
||||
* Added CPU training support for TorchTune
|
||||
### Deploy and Monitoring of Agents
|
||||
* Consistent view of client and server tool calls in telemetry
|
||||
### Better Engineering
|
||||
* Made tests more data-driven for consistent evaluation
|
||||
* Fixed documentation links and improved API reference generation
|
||||
* Various small fixes for build scripts and system reliability
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
# v0.1.3
|
||||
Published on: 2025-02-14T20:24:32Z
|
||||
|
||||
## 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
|
||||
|
||||
## 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
|
||||
|
||||
|
||||
---
|
||||
|
||||
# v0.1.2
|
||||
Published on: 2025-02-07T22:06:49Z
|
||||
|
||||
# TL;DR
|
||||
- Several stabilizations to development flows after the switch to `uv`
|
||||
- Migrated CI workflows to new OSS repo - [llama-stack-ops](https://github.com/meta-llama/llama-stack-ops)
|
||||
- Added automated rebuilds for ReadTheDocs
|
||||
- Llama Stack server supports HTTPS
|
||||
- Added system prompt overrides support
|
||||
- Several bug fixes and improvements to documentation (check out Kubernetes deployment guide by @terrytangyuan )
|
||||
|
||||
# TL;DR
|
||||
- Several stabilizations to development flows after the switch to `uv`
|
||||
- Migrated CI workflows to new OSS repo - [llama-stack-ops](https://github.com/meta-llama/llama-stack-ops)
|
||||
- Added automated rebuilds for ReadTheDocs
|
||||
- Llama Stack server supports HTTPS
|
||||
- Added system prompt overrides support
|
||||
- Several bug fixes and improvements to documentation (check out Kubernetes deployment guide by @terrytangyuan )
|
||||
|
||||
|
||||
---
|
||||
|
||||
# v0.1.1
|
||||
Published on: 2025-02-02T02:29:24Z
|
||||
|
||||
A bunch of small / big improvements everywhere including support for Windows, switching to `uv` and many provider improvements.
|
||||
|
||||
A bunch of small / big improvements everywhere including support for Windows, switching to `uv` and many provider improvements.
|
||||
|
||||
|
||||
---
|
||||
|
||||
# v0.1.0
|
||||
Published on: 2025-01-24T17:47:47Z
|
||||
|
||||
We are excited to announce a stable API release of Llama Stack, which enables developers to build RAG applications and Agents using tools and safety shields, monitor and those agents with telemetry, and evaluate the agent with scoring functions.
|
||||
|
||||
## Context
|
||||
GenAI application developers need more than just an LLM - they need to integrate tools, connect with their data sources, establish guardrails, and ground the LLM responses effectively. Currently, developers must piece together various tools and APIs, complicating the development lifecycle and increasing costs. The result is that developers are spending more time on these integrations rather than focusing on the application logic itself. The bespoke coupling of components also makes it challenging to adopt state-of-the-art solutions in the rapidly evolving GenAI space. This is particularly difficult for open models like Llama, as best practices are not widely established in the open.
|
||||
|
||||
Llama Stack was created to provide developers with a comprehensive and coherent interface that simplifies AI application development and codifies best practices across the Llama ecosystem. Since our launch in September 2024, we have seen a huge uptick in interest in Llama Stack APIs by both AI developers and from partners building AI services with Llama models. Partners like Nvidia, Fireworks, and Ollama have collaborated with us to develop implementations across various APIs, including inference, memory, and safety.
|
||||
|
||||
With Llama Stack, you can easily build a RAG agent which can also search the web, do complex math, and custom tool calling. You can use telemetry to inspect those traces, and convert telemetry into evals datasets. And with Llama Stack’s plugin architecture and prepackage distributions, you choose to run your agent anywhere - in the cloud with our partners, deploy your own environment using virtualenv, conda, or Docker, operate locally with Ollama, or even run on mobile devices with our SDKs. Llama Stack offers unprecedented flexibility while also simplifying the developer experience.
|
||||
|
||||
## Release
|
||||
After iterating on the APIs for the last 3 months, today we’re launching a stable release (V1) of the Llama Stack APIs and the corresponding llama-stack server and client packages(v0.1.0). We now have automated tests for providers. These tests make sure that all provider implementations are verified. Developers can now easily and reliably select distributions or providers based on their specific requirements.
|
||||
|
||||
There are example standalone apps in llama-stack-apps.
|
||||
|
||||
|
||||
## Key Features of this release
|
||||
|
||||
- **Unified API Layer**
|
||||
- Inference: Run LLM models
|
||||
- RAG: Store and retrieve knowledge for RAG
|
||||
- Agents: Build multi-step agentic workflows
|
||||
- Tools: Register tools that can be called by the agent
|
||||
- Safety: Apply content filtering and safety policies
|
||||
- Evaluation: Test model and agent quality
|
||||
- Telemetry: Collect and analyze usage data and complex agentic traces
|
||||
- Post Training ( Coming Soon ): Fine tune models for specific use cases
|
||||
|
||||
- **Rich Provider Ecosystem**
|
||||
- Local Development: Meta's Reference, Ollama
|
||||
- Cloud: Fireworks, Together, Nvidia, AWS Bedrock, Groq, Cerebras
|
||||
- On-premises: Nvidia NIM, vLLM, TGI, Dell-TGI
|
||||
- On-device: iOS and Android support
|
||||
|
||||
- **Built for Production**
|
||||
- Pre-packaged distributions for common deployment scenarios
|
||||
- Backwards compatibility across model versions
|
||||
- Comprehensive evaluation capabilities
|
||||
- Full observability and monitoring
|
||||
|
||||
- **Multiple developer interfaces**
|
||||
- CLI: Command line interface
|
||||
- Python SDK
|
||||
- Swift iOS SDK
|
||||
- Kotlin Android SDK
|
||||
|
||||
- **Sample llama stack applications**
|
||||
- Python
|
||||
- iOS
|
||||
- Android
|
||||
|
||||
|
||||
We are excited to announce a stable API release of Llama Stack, which enables developers to build RAG applications and Agents using tools and safety shields, monitor and those agents with telemetry, and evaluate the agent with scoring functions.
|
||||
|
||||
## Context
|
||||
GenAI application developers need more than just an LLM - they need to integrate tools, connect with their data sources, establish guardrails, and ground the LLM responses effectively. Currently, developers must piece together various tools and APIs, complicating the development lifecycle and increasing costs. The result is that developers are spending more time on these integrations rather than focusing on the application logic itself. The bespoke coupling of components also makes it challenging to adopt state-of-the-art solutions in the rapidly evolving GenAI space. This is particularly difficult for open models like Llama, as best practices are not widely established in the open.
|
||||
|
||||
Llama Stack was created to provide developers with a comprehensive and coherent interface that simplifies AI application development and codifies best practices across the Llama ecosystem. Since our launch in September 2024, we have seen a huge uptick in interest in Llama Stack APIs by both AI developers and from partners building AI services with Llama models. Partners like Nvidia, Fireworks, and Ollama have collaborated with us to develop implementations across various APIs, including inference, memory, and safety.
|
||||
|
||||
With Llama Stack, you can easily build a RAG agent which can also search the web, do complex math, and custom tool calling. You can use telemetry to inspect those traces, and convert telemetry into evals datasets. And with Llama Stack’s plugin architecture and prepackage distributions, you choose to run your agent anywhere - in the cloud with our partners, deploy your own environment using virtualenv, conda, or Docker, operate locally with Ollama, or even run on mobile devices with our SDKs. Llama Stack offers unprecedented flexibility while also simplifying the developer experience.
|
||||
|
||||
## Release
|
||||
After iterating on the APIs for the last 3 months, today we’re launching a stable release (V1) of the Llama Stack APIs and the corresponding llama-stack server and client packages(v0.1.0). We now have automated tests for providers. These tests make sure that all provider implementations are verified. Developers can now easily and reliably select distributions or providers based on their specific requirements.
|
||||
|
||||
There are example standalone apps in llama-stack-apps.
|
||||
|
||||
|
||||
## Key Features of this release
|
||||
|
||||
- **Unified API Layer**
|
||||
- Inference: Run LLM models
|
||||
- RAG: Store and retrieve knowledge for RAG
|
||||
- Agents: Build multi-step agentic workflows
|
||||
- Tools: Register tools that can be called by the agent
|
||||
- Safety: Apply content filtering and safety policies
|
||||
- Evaluation: Test model and agent quality
|
||||
- Telemetry: Collect and analyze usage data and complex agentic traces
|
||||
- Post Training ( Coming Soon ): Fine tune models for specific use cases
|
||||
|
||||
- **Rich Provider Ecosystem**
|
||||
- Local Development: Meta's Reference, Ollama
|
||||
- Cloud: Fireworks, Together, Nvidia, AWS Bedrock, Groq, Cerebras
|
||||
- On-premises: Nvidia NIM, vLLM, TGI, Dell-TGI
|
||||
- On-device: iOS and Android support
|
||||
|
||||
- **Built for Production**
|
||||
- Pre-packaged distributions for common deployment scenarios
|
||||
- Backwards compatibility across model versions
|
||||
- Comprehensive evaluation capabilities
|
||||
- Full observability and monitoring
|
||||
|
||||
- **Multiple developer interfaces**
|
||||
- CLI: Command line interface
|
||||
- Python SDK
|
||||
- Swift iOS SDK
|
||||
- Kotlin Android SDK
|
||||
|
||||
- **Sample llama stack applications**
|
||||
- Python
|
||||
- iOS
|
||||
- Android
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -365,8 +365,8 @@ Published on: 2025-01-22T22:24:01Z
|
|||
# v0.0.63
|
||||
Published on: 2024-12-18T07:17:43Z
|
||||
|
||||
A small but important bug-fix release to update the URL datatype for the client-SDKs. The issue affected multimodal agentic turns especially.
|
||||
|
||||
A small but important bug-fix release to update the URL datatype for the client-SDKs. The issue affected multimodal agentic turns especially.
|
||||
|
||||
**Full Changelog**: https://github.com/meta-llama/llama-stack/compare/v0.0.62...v0.0.63
|
||||
|
||||
---
|
||||
|
|
@ -402,39 +402,39 @@ Published on: 2024-11-22T00:36:09Z
|
|||
# v0.0.53
|
||||
Published on: 2024-11-20T22:18:00Z
|
||||
|
||||
🚀 Initial Release Notes for Llama Stack!
|
||||
|
||||
### Added
|
||||
- Resource-oriented design for models, shields, memory banks, datasets and eval tasks
|
||||
- Persistence for registered objects with distribution
|
||||
- Ability to persist memory banks created for FAISS
|
||||
- PostgreSQL KVStore implementation
|
||||
- Environment variable placeholder support in run.yaml files
|
||||
- Comprehensive Zero-to-Hero notebooks and quickstart guides
|
||||
- Support for quantized models in Ollama
|
||||
- Vision models support for Together, Fireworks, Meta-Reference, and Ollama, and vLLM
|
||||
- Bedrock distribution with safety shields support
|
||||
- Evals API with task registration and scoring functions
|
||||
- MMLU and SimpleQA benchmark scoring functions
|
||||
- Huggingface dataset provider integration for benchmarks
|
||||
- Support for custom dataset registration from local paths
|
||||
- Benchmark evaluation CLI tools with visualization tables
|
||||
- RAG evaluation scoring functions and metrics
|
||||
- Local persistence for datasets and eval tasks
|
||||
|
||||
### Changed
|
||||
- Split safety into distinct providers (llama-guard, prompt-guard, code-scanner)
|
||||
- Changed provider naming convention (`impls` → `inline`, `adapters` → `remote`)
|
||||
- Updated API signatures for dataset and eval task registration
|
||||
- Restructured folder organization for providers
|
||||
- Enhanced Docker build configuration
|
||||
- Added version prefixing for REST API routes
|
||||
- Enhanced evaluation task registration workflow
|
||||
- Improved benchmark evaluation output formatting
|
||||
- Restructured evals folder organization for better modularity
|
||||
|
||||
### Removed
|
||||
- `llama stack configure` command
|
||||
|
||||
🚀 Initial Release Notes for Llama Stack!
|
||||
|
||||
### Added
|
||||
- Resource-oriented design for models, shields, memory banks, datasets and eval tasks
|
||||
- Persistence for registered objects with distribution
|
||||
- Ability to persist memory banks created for FAISS
|
||||
- PostgreSQL KVStore implementation
|
||||
- Environment variable placeholder support in run.yaml files
|
||||
- Comprehensive Zero-to-Hero notebooks and quickstart guides
|
||||
- Support for quantized models in Ollama
|
||||
- Vision models support for Together, Fireworks, Meta-Reference, and Ollama, and vLLM
|
||||
- Bedrock distribution with safety shields support
|
||||
- Evals API with task registration and scoring functions
|
||||
- MMLU and SimpleQA benchmark scoring functions
|
||||
- Huggingface dataset provider integration for benchmarks
|
||||
- Support for custom dataset registration from local paths
|
||||
- Benchmark evaluation CLI tools with visualization tables
|
||||
- RAG evaluation scoring functions and metrics
|
||||
- Local persistence for datasets and eval tasks
|
||||
|
||||
### Changed
|
||||
- Split safety into distinct providers (llama-guard, prompt-guard, code-scanner)
|
||||
- Changed provider naming convention (`impls` → `inline`, `adapters` → `remote`)
|
||||
- Updated API signatures for dataset and eval task registration
|
||||
- Restructured folder organization for providers
|
||||
- Enhanced Docker build configuration
|
||||
- Added version prefixing for REST API routes
|
||||
- Enhanced evaluation task registration workflow
|
||||
- Improved benchmark evaluation output formatting
|
||||
- Restructured evals folder organization for better modularity
|
||||
|
||||
### Removed
|
||||
- `llama stack configure` command
|
||||
|
||||
|
||||
---
|
||||
|
|
|
|||
|
|
@ -1,35 +1,35 @@
|
|||
@ECHO OFF
|
||||
|
||||
pushd %~dp0
|
||||
|
||||
REM Command file for Sphinx documentation
|
||||
|
||||
if "%SPHINXBUILD%" == "" (
|
||||
set SPHINXBUILD=sphinx-build
|
||||
)
|
||||
set SOURCEDIR=.
|
||||
set BUILDDIR=_build
|
||||
|
||||
%SPHINXBUILD% >NUL 2>NUL
|
||||
if errorlevel 9009 (
|
||||
echo.
|
||||
echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
|
||||
echo.installed, then set the SPHINXBUILD environment variable to point
|
||||
echo.to the full path of the 'sphinx-build' executable. Alternatively you
|
||||
echo.may add the Sphinx directory to PATH.
|
||||
echo.
|
||||
echo.If you don't have Sphinx installed, grab it from
|
||||
echo.https://www.sphinx-doc.org/
|
||||
exit /b 1
|
||||
)
|
||||
|
||||
if "%1" == "" goto help
|
||||
|
||||
%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
goto end
|
||||
|
||||
:help
|
||||
%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
|
||||
:end
|
||||
popd
|
||||
@ECHO OFF
|
||||
|
||||
pushd %~dp0
|
||||
|
||||
REM Command file for Sphinx documentation
|
||||
|
||||
if "%SPHINXBUILD%" == "" (
|
||||
set SPHINXBUILD=sphinx-build
|
||||
)
|
||||
set SOURCEDIR=.
|
||||
set BUILDDIR=_build
|
||||
|
||||
%SPHINXBUILD% >NUL 2>NUL
|
||||
if errorlevel 9009 (
|
||||
echo.
|
||||
echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
|
||||
echo.installed, then set the SPHINXBUILD environment variable to point
|
||||
echo.to the full path of the 'sphinx-build' executable. Alternatively you
|
||||
echo.may add the Sphinx directory to PATH.
|
||||
echo.
|
||||
echo.If you don't have Sphinx installed, grab it from
|
||||
echo.https://www.sphinx-doc.org/
|
||||
exit /b 1
|
||||
)
|
||||
|
||||
if "%1" == "" goto help
|
||||
|
||||
%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
goto end
|
||||
|
||||
:help
|
||||
%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
|
||||
:end
|
||||
popd
|
||||
|
|
|
|||
|
|
@ -1,16 +1,16 @@
|
|||
sphinx==8.1.3
|
||||
myst-parser
|
||||
linkify
|
||||
myst-parser
|
||||
-e git+https://github.com/pytorch/pytorch_sphinx_theme.git#egg=pytorch_sphinx_theme
|
||||
sphinx-rtd-theme>=1.0.0
|
||||
sphinx_autobuild
|
||||
sphinx==8.1.3
|
||||
sphinx-copybutton
|
||||
sphinx-design
|
||||
sphinx-pdj-theme
|
||||
sphinx_rtd_dark_mode
|
||||
sphinx-rtd-theme>=1.0.0
|
||||
sphinx-tabs
|
||||
sphinx_autobuild
|
||||
sphinx_rtd_dark_mode
|
||||
sphinxcontrib-mermaid
|
||||
sphinxcontrib-openapi
|
||||
sphinxcontrib-redoc
|
||||
sphinxcontrib-mermaid
|
||||
sphinxcontrib-video
|
||||
tomli
|
||||
|
|
|
|||
|
|
@ -86,11 +86,11 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
|
|||
llama stack build --template ollama --image-type conda
|
||||
```
|
||||
**Expected Output:**
|
||||
```
|
||||
```bash
|
||||
...
|
||||
Build Successful! Next steps:
|
||||
1. Set the environment variables: LLAMA_STACK_PORT, OLLAMA_URL, INFERENCE_MODEL, SAFETY_MODEL
|
||||
2. `llama stack run /Users/<username>/.llama/distributions/llamastack-ollama/ollama-run.yaml
|
||||
Build Successful!
|
||||
You can find the newly-built template here: ~/.llama/distributions/ollama/ollama-run.yaml
|
||||
You can run the new Llama Stack Distro via: llama stack run ~/.llama/distributions/ollama/ollama-run.yaml --image-type conda
|
||||
```
|
||||
|
||||
3. **Set the ENV variables by exporting them to the terminal**:
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ import yaml
|
|||
from prompt_toolkit import prompt
|
||||
from prompt_toolkit.completion import WordCompleter
|
||||
from prompt_toolkit.validation import Validator
|
||||
from termcolor import cprint
|
||||
from termcolor import colored, cprint
|
||||
|
||||
from llama_stack.cli.stack.utils import ImageType
|
||||
from llama_stack.cli.table import print_table
|
||||
|
|
@ -389,6 +389,11 @@ def _run_stack_build_command_from_build_config(
|
|||
shutil.copy(path, run_config_file)
|
||||
|
||||
cprint("Build Successful!", color="green")
|
||||
cprint("You can find the newly-built template here: " + colored(template_path, "light_blue"))
|
||||
cprint(
|
||||
"You can run the new Llama Stack distro via: "
|
||||
+ colored(f"llama stack run {template_path} --image-type {build_config.image_type}", "light_blue")
|
||||
)
|
||||
return template_path
|
||||
else:
|
||||
return _generate_run_config(build_config, build_dir, image_name)
|
||||
|
|
|
|||
|
|
@ -119,7 +119,7 @@ class StackRun(Subcommand):
|
|||
|
||||
if not config_file.is_file():
|
||||
self.parser.error(
|
||||
f"Config file must be a valid file path, '{config_file}’ is not a file: type={type(config_file)}"
|
||||
f"Config file must be a valid file path, '{config_file}' is not a file: type={type(config_file)}"
|
||||
)
|
||||
|
||||
logger.info(f"Using run configuration: {config_file}")
|
||||
|
|
|
|||
|
|
@ -47,14 +47,13 @@ def get_provider_dependencies(
|
|||
providers = config.distribution_spec.providers
|
||||
deps = []
|
||||
registry = get_provider_registry(config)
|
||||
|
||||
for api_str, provider_or_providers in providers.items():
|
||||
providers_for_api = registry[Api(api_str)]
|
||||
|
||||
providers = provider_or_providers if isinstance(provider_or_providers, list) else [provider_or_providers]
|
||||
|
||||
for provider in providers:
|
||||
# Providers from BuildConfig and RunConfig are subtly different – not great
|
||||
# Providers from BuildConfig and RunConfig are subtly different - not great
|
||||
provider_type = provider if isinstance(provider, str) else provider.provider_type
|
||||
|
||||
if provider_type not in providers_for_api:
|
||||
|
|
|
|||
|
|
@ -1,3 +1,5 @@
|
|||
#!/usr/bin/env bash
|
||||
|
||||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
streamlit
|
||||
pandas
|
||||
llama-stack-client>=0.2.1
|
||||
streamlit-option-menu
|
||||
llama-stack>=0.2.1
|
||||
llama-stack-client>=0.2.1
|
||||
pandas
|
||||
streamlit
|
||||
streamlit-option-menu
|
||||
|
|
|
|||
0
llama_stack/models/llama/llama4/tokenizer.model
Executable file → Normal file
0
llama_stack/models/llama/llama4/tokenizer.model
Executable file → Normal file
|
|
@ -30,7 +30,7 @@ class TelemetryConfig(BaseModel):
|
|||
)
|
||||
service_name: str = Field(
|
||||
# service name is always the same, use zero-width space to avoid clutter
|
||||
default="",
|
||||
default="",
|
||||
description="The service name to use for telemetry",
|
||||
)
|
||||
sinks: List[TelemetrySink] = Field(
|
||||
|
|
@ -52,7 +52,7 @@ class TelemetryConfig(BaseModel):
|
|||
@classmethod
|
||||
def sample_run_config(cls, __distro_dir__: str, db_name: str = "trace_store.db") -> Dict[str, Any]:
|
||||
return {
|
||||
"service_name": "${env.OTEL_SERVICE_NAME:}",
|
||||
"service_name": "${env.OTEL_SERVICE_NAME:}",
|
||||
"sinks": "${env.TELEMETRY_SINKS:console,sqlite}",
|
||||
"sqlite_db_path": "${env.SQLITE_STORE_DIR:" + __distro_dir__ + "}/" + db_name,
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,18 +1,18 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
from .config import BedrockConfig
|
||||
|
||||
|
||||
async def get_adapter_impl(config: BedrockConfig, _deps):
|
||||
from .bedrock import BedrockInferenceAdapter
|
||||
|
||||
assert isinstance(config, BedrockConfig), f"Unexpected config type: {type(config)}"
|
||||
|
||||
impl = BedrockInferenceAdapter(config)
|
||||
|
||||
await impl.initialize()
|
||||
|
||||
return impl
|
||||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
from .config import BedrockConfig
|
||||
|
||||
|
||||
async def get_adapter_impl(config: BedrockConfig, _deps):
|
||||
from .bedrock import BedrockInferenceAdapter
|
||||
|
||||
assert isinstance(config, BedrockConfig), f"Unexpected config type: {type(config)}"
|
||||
|
||||
impl = BedrockInferenceAdapter(config)
|
||||
|
||||
await impl.initialize()
|
||||
|
||||
return impl
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.providers.utils.bedrock.config import BedrockBaseConfig
|
||||
|
||||
|
||||
class BedrockConfig(BedrockBaseConfig):
|
||||
pass
|
||||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.providers.utils.bedrock.config import BedrockBaseConfig
|
||||
|
||||
|
||||
class BedrockConfig(BedrockBaseConfig):
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -12,8 +12,8 @@ import requests
|
|||
from llama_stack.apis.inference import Message
|
||||
from llama_stack.apis.safety import RunShieldResponse, Safety, SafetyViolation, ViolationLevel
|
||||
from llama_stack.apis.shields import Shield
|
||||
from llama_stack.distribution.library_client import convert_pydantic_to_json_value
|
||||
from llama_stack.providers.datatypes import ShieldsProtocolPrivate
|
||||
from llama_stack.providers.utils.inference.openai_compat import convert_message_to_openai_dict_new
|
||||
|
||||
from .config import NVIDIASafetyConfig
|
||||
|
||||
|
|
@ -28,7 +28,6 @@ class NVIDIASafetyAdapter(Safety, ShieldsProtocolPrivate):
|
|||
Args:
|
||||
config (NVIDIASafetyConfig): The configuration containing the guardrails service URL and config ID.
|
||||
"""
|
||||
print(f"Initializing NVIDIASafetyAdapter({config.guardrails_service_url})...")
|
||||
self.config = config
|
||||
|
||||
async def initialize(self) -> None:
|
||||
|
|
@ -127,9 +126,10 @@ class NeMoGuardrails:
|
|||
Raises:
|
||||
requests.HTTPError: If the POST request fails.
|
||||
"""
|
||||
request_messages = [await convert_message_to_openai_dict_new(message) for message in messages]
|
||||
request_data = {
|
||||
"model": self.model,
|
||||
"messages": convert_pydantic_to_json_value(messages),
|
||||
"messages": request_messages,
|
||||
"temperature": self.temperature,
|
||||
"top_p": 1,
|
||||
"frequency_penalty": 0,
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -79,7 +79,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/trace_store.db
|
||||
tool_runtime:
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -71,7 +71,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -54,7 +54,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -60,7 +60,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -43,7 +43,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -68,7 +68,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -88,7 +88,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/trace_store.db
|
||||
tool_runtime:
|
||||
|
|
|
|||
|
|
@ -81,7 +81,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/trace_store.db
|
||||
tool_runtime:
|
||||
|
|
|
|||
|
|
@ -51,7 +51,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/trace_store.db
|
||||
tool_runtime:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -45,7 +45,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -78,7 +78,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -43,7 +43,7 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
|
||||
service_name: ${env.OTEL_SERVICE_NAME:}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/trace_store.db
|
||||
eval:
|
||||
|
|
|
|||
|
|
@ -144,15 +144,25 @@ exclude = [
|
|||
|
||||
[tool.ruff.lint]
|
||||
select = [
|
||||
"B", # flake8-bugbear
|
||||
"B9", # flake8-bugbear subset
|
||||
"C", # comprehensions
|
||||
"E", # pycodestyle
|
||||
"F", # Pyflakes
|
||||
"N", # Naming
|
||||
"W", # Warnings
|
||||
"DTZ", # datetime rules
|
||||
"I", # isort (imports order)
|
||||
"B", # flake8-bugbear
|
||||
"B9", # flake8-bugbear subset
|
||||
"C", # comprehensions
|
||||
"E", # pycodestyle
|
||||
"F", # Pyflakes
|
||||
"N", # Naming
|
||||
"W", # Warnings
|
||||
"DTZ", # datetime rules
|
||||
"I", # isort (imports order)
|
||||
"RUF001", # Checks for ambiguous Unicode characters in strings
|
||||
"RUF002", # Checks for ambiguous Unicode characters in docstrings
|
||||
"RUF003", # Checks for ambiguous Unicode characters in comments
|
||||
"PLC2401", # Checks for the use of non-ASCII characters in variable names
|
||||
"PLC2403", # Checks for the use of non-ASCII characters in import statements
|
||||
"PLE2510", # Checks for strings that contain the control character BS.
|
||||
"PLE2512", # Checks for strings that contain the raw control character SUB.
|
||||
"PLE2513", # Checks for strings that contain the raw control character ESC.
|
||||
"PLE2514", # Checks for strings that contain the raw control character NUL (0 byte).
|
||||
"PLE2515", # Checks for strings that contain the zero width space character.
|
||||
]
|
||||
ignore = [
|
||||
# The following ignores are desired by the project maintainers.
|
||||
|
|
@ -165,10 +175,18 @@ ignore = [
|
|||
# These are the additional ones we started ignoring after moving to ruff. We should look into each one of them later.
|
||||
"C901", # Complexity of the function is too high
|
||||
]
|
||||
unfixable = [
|
||||
"PLE2515",
|
||||
] # Do not fix this automatically since ruff will replace the zero-width space with \u200b - let's do it manually
|
||||
|
||||
# Ignore the following errors for the following files
|
||||
[tool.ruff.lint.per-file-ignores]
|
||||
"tests/**/*.py" = ["DTZ"] # Ignore datetime rules for tests
|
||||
"llama_stack/providers/inline/scoring/basic/utils/ifeval_utils.py" = ["RUF001"]
|
||||
"llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_multiple_choice_answer.py" = [
|
||||
"RUF001",
|
||||
"PLE2515",
|
||||
]
|
||||
|
||||
[tool.mypy]
|
||||
mypy_path = ["llama_stack"]
|
||||
|
|
|
|||
|
|
@ -4,7 +4,6 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import json
|
||||
import os
|
||||
import unittest
|
||||
from typing import Any
|
||||
|
|
@ -139,8 +138,8 @@ class TestNVIDIASafetyAdapter(unittest.TestCase):
|
|||
data={
|
||||
"model": shield_id,
|
||||
"messages": [
|
||||
json.loads(messages[0].model_dump_json()),
|
||||
json.loads(messages[1].model_dump_json()),
|
||||
{"role": "user", "content": "Hello, how are you?"},
|
||||
{"role": "assistant", "content": "I'm doing well, thank you for asking!"},
|
||||
],
|
||||
"temperature": 1.0,
|
||||
"top_p": 1,
|
||||
|
|
@ -193,8 +192,8 @@ class TestNVIDIASafetyAdapter(unittest.TestCase):
|
|||
data={
|
||||
"model": shield_id,
|
||||
"messages": [
|
||||
json.loads(messages[0].model_dump_json()),
|
||||
json.loads(messages[1].model_dump_json()),
|
||||
{"role": "user", "content": "Hello, how are you?"},
|
||||
{"role": "assistant", "content": "I'm doing well, thank you for asking!"},
|
||||
],
|
||||
"temperature": 1.0,
|
||||
"top_p": 1,
|
||||
|
|
@ -269,8 +268,8 @@ class TestNVIDIASafetyAdapter(unittest.TestCase):
|
|||
data={
|
||||
"model": shield_id,
|
||||
"messages": [
|
||||
json.loads(messages[0].model_dump_json()),
|
||||
json.loads(messages[1].model_dump_json()),
|
||||
{"role": "user", "content": "Hello, how are you?"},
|
||||
{"role": "assistant", "content": "I'm doing well, thank you for asking!"},
|
||||
],
|
||||
"temperature": 1.0,
|
||||
"top_p": 1,
|
||||
|
|
|
|||
|
|
@ -1,3 +1,5 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue