forked from phoenix-oss/llama-stack-mirror
a5c57cd381
# What does this PR do? PR #639 introduced the notion of Tools API and ability to invoke tools through API just as any resource. This PR changes the Agents to start using the Tools API to invoke tools. Major changes include: 1) Ability to specify tool groups with AgentConfig 2) Agent gets the corresponding tool definitions for the specified tools and pass along to the model 3) Attachements are now named as Documents and their behavior is mostly unchanged from user perspective 4) You can specify args that can be injected to a tool call through Agent config. This is especially useful in case of memory tool, where you want the tool to operate on a specific memory bank. 5) You can also register tool groups with args, which lets the agent inject these as well into the tool call. 6) All tests have been migrated to use new tools API and fixtures including client SDK tests 7) Telemetry just works with tools API because of our trace protocol decorator ## Test Plan ``` pytest -s -v -k fireworks llama_stack/providers/tests/agents/test_agents.py \ --safety-shield=meta-llama/Llama-Guard-3-8B \ --inference-model=meta-llama/Llama-3.1-8B-Instruct pytest -s -v -k together llama_stack/providers/tests/tools/test_tools.py \ --safety-shield=meta-llama/Llama-Guard-3-8B \ --inference-model=meta-llama/Llama-3.1-8B-Instruct LLAMA_STACK_CONFIG="/Users/dineshyv/.llama/distributions/llamastack-together/together-run.yaml" pytest -v tests/client-sdk/agents/test_agents.py ``` run.yaml: https://gist.github.com/dineshyv/0365845ad325e1c2cab755788ccc5994 Notebook: https://colab.research.google.com/drive/1ck7hXQxRl6UvT-ijNRZ-gMZxH1G3cN2d?usp=sharing
117 lines
3.2 KiB
YAML
117 lines
3.2 KiB
YAML
version: '2'
|
|
image_name: meta-reference-quantized-gpu
|
|
conda_env: meta-reference-quantized-gpu
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- inference
|
|
- memory
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
- tool_runtime
|
|
providers:
|
|
inference:
|
|
- provider_id: meta-reference-inference
|
|
provider_type: inline::meta-reference-quantized
|
|
config:
|
|
model: ${env.INFERENCE_MODEL}
|
|
max_seq_len: 4096
|
|
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
|
|
quantization:
|
|
type: fp8
|
|
- provider_id: sentence-transformers
|
|
provider_type: inline::sentence-transformers
|
|
config: {}
|
|
memory:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/faiss_store.db
|
|
safety:
|
|
- provider_id: llama-guard
|
|
provider_type: inline::llama-guard
|
|
config: {}
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/agents_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
|
|
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-quantized-gpu/trace_store.db}
|
|
eval:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config: {}
|
|
datasetio:
|
|
- provider_id: huggingface
|
|
provider_type: remote::huggingface
|
|
config: {}
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config: {}
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
config: {}
|
|
- provider_id: llm-as-judge
|
|
provider_type: inline::llm-as-judge
|
|
config: {}
|
|
- provider_id: braintrust
|
|
provider_type: inline::braintrust
|
|
config:
|
|
openai_api_key: ${env.OPENAI_API_KEY:}
|
|
tool_runtime:
|
|
- provider_id: brave-search
|
|
provider_type: remote::brave-search
|
|
config:
|
|
api_key: ${env.BRAVE_SEARCH_API_KEY:}
|
|
max_results: 3
|
|
- provider_id: tavily-search
|
|
provider_type: remote::tavily-search
|
|
config:
|
|
api_key: ${env.TAVILY_SEARCH_API_KEY:}
|
|
max_results: 3
|
|
- provider_id: code-interpreter
|
|
provider_type: inline::code-interpreter
|
|
config: {}
|
|
- provider_id: memory-runtime
|
|
provider_type: inline::memory-runtime
|
|
config: {}
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/registry.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: ${env.INFERENCE_MODEL}
|
|
provider_id: meta-reference-inference
|
|
model_type: llm
|
|
- metadata:
|
|
embedding_dimension: 384
|
|
model_id: all-MiniLM-L6-v2
|
|
provider_id: sentence-transformers
|
|
model_type: embedding
|
|
shields: []
|
|
memory_banks: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
eval_tasks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::websearch
|
|
provider_id: tavily-search
|
|
- toolgroup_id: builtin::memory
|
|
provider_id: memory-runtime
|
|
- toolgroup_id: builtin::code_interpreter
|
|
provider_id: code-interpreter
|