phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 04:50:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

simplify setup

Browse source
This commit is contained in:
Xi Yan 2025-03-03 15:41:10 -08:00
parent 5dbce05ee0
commit f598a4464e
1 changed files with 575 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

599
docs/notebooks/Llama_Stack_Agent_Workflows.ipynb
View file

@ -43,9 +43,566 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 114,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Not in Google Colab environment\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Warning: `bwrap` is not available. Code interpreter tool will not work correctly.\n"
]
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Using config <span style=\"color: #000080; text-decoration-color: #000080\">fireworks</span>:\n",
"</pre>\n"
],
"text/plain": [
"Using config \u001b[34mfireworks\u001b[0m:\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">apis:\n",
"- agents\n",
"- datasetio\n",
"- eval\n",
"- inference\n",
"- safety\n",
"- scoring\n",
"- telemetry\n",
"- tool_runtime\n",
"- vector_io\n",
"benchmarks: <span style=\"font-weight: bold\">[]</span>\n",
"container_image: null\n",
"datasets: <span style=\"font-weight: bold\">[]</span>\n",
"image_name: fireworks\n",
"metadata_store:\n",
" db_path: <span style=\"color: #800080; text-decoration-color: #800080\">/Users/xiyan/.llama/distributions/fireworks/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">registry.db</span>\n",
" namespace: null\n",
" type: sqlite\n",
"models:\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-v3p1-8b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-8B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-v3p1-70b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-70B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-v3p1-405b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-405B-Instruct-FP8\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-v3p2-1b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-1B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-v3p2-3b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-3B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-11B-Vision-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-90B-Vision-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-v3p3-70b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.3</span>-70B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8b\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8b\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8B\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8b\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: accounts/fireworks/models/llama-guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-11b-vision\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-11b-vision\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-11B-Vision\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-11b-vision\n",
"- metadata:\n",
" context_length: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">8192</span>\n",
" embedding_dimension: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">768</span>\n",
" model_id: nomic-ai/nomic-embed-text-v1.<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span>\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - embedding\n",
" provider_id: fireworks\n",
" provider_model_id: nomic-ai/nomic-embed-text-v1.<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">5</span>\n",
"- metadata:\n",
" embedding_dimension: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">384</span>\n",
" model_id: all-MiniLM-L6-v2\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - embedding\n",
" provider_id: sentence-transformers\n",
" provider_model_id: null\n",
"providers:\n",
" agents:\n",
" - config:\n",
" persistence_store:\n",
" db_path: <span style=\"color: #800080; text-decoration-color: #800080\">/Users/xiyan/.llama/distributions/fireworks/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">agents_store.db</span>\n",
" namespace: null\n",
" type: sqlite\n",
" provider_id: meta-reference\n",
" provider_type: inline::meta-reference\n",
" datasetio:\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: huggingface\n",
" provider_type: remote::huggingface\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: localfs\n",
" provider_type: inline::localfs\n",
" eval:\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: meta-reference\n",
" provider_type: inline::meta-reference\n",
" inference:\n",
" - config:\n",
" api_key: <span style=\"color: #008000; text-decoration-color: #008000\">'********'</span>\n",
" url: <span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">https://api.fireworks.ai/inference/v1</span>\n",
" provider_id: fireworks\n",
" provider_type: remot<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::f</span>ireworks\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: sentence-transformers\n",
" provider_type: inline::sentence-transformers\n",
" safety:\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: llama-guard\n",
" provider_type: inline::llama-guard\n",
" scoring:\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: basic\n",
" provider_type: inlin<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::ba</span>sic\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: llm-as-judge\n",
" provider_type: inline::llm-as-judge\n",
" - config:\n",
" openai_api_key: <span style=\"color: #008000; text-decoration-color: #008000\">'********'</span>\n",
" provider_id: braintrust\n",
" provider_type: inlin<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::b</span>raintrust\n",
" telemetry:\n",
" - config:\n",
" service_name: llama-stack\n",
" sinks: sqlite\n",
" sqlite_db_path: <span style=\"color: #800080; text-decoration-color: #800080\">/Users/xiyan/.llama/distributions/fireworks/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">trace_store.db</span>\n",
" provider_id: meta-reference\n",
" provider_type: inline::meta-reference\n",
" tool_runtime:\n",
" - config:\n",
" api_key: <span style=\"color: #008000; text-decoration-color: #008000\">'********'</span>\n",
" max_results: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>\n",
" provider_id: brave-search\n",
" provider_type: remot<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::b</span>rave-search\n",
" - config:\n",
" api_key: <span style=\"color: #008000; text-decoration-color: #008000\">'********'</span>\n",
" max_results: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>\n",
" provider_id: tavily-search\n",
" provider_type: remote::tavily-search\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: code-interpreter\n",
" provider_type: inlin<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::c</span>ode-interpreter\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: rag-runtime\n",
" provider_type: inline::rag-runtime\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: model-context-protocol\n",
" provider_type: remote::model-context-protocol\n",
" vector_io:\n",
" - config:\n",
" kvstore:\n",
" db_path: <span style=\"color: #800080; text-decoration-color: #800080\">/Users/xiyan/.llama/distributions/fireworks/</span><span style=\"color: #ff00ff; text-decoration-color: #ff00ff\">faiss_store.db</span>\n",
" namespace: null\n",
" type: sqlite\n",
" provider_id: faiss\n",
" provider_type: inlin<span style=\"color: #00ff00; text-decoration-color: #00ff00; font-weight: bold\">e::fa</span>iss\n",
"scoring_fns: <span style=\"font-weight: bold\">[]</span>\n",
"server:\n",
" port: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">8321</span>\n",
" tls_certfile: null\n",
" tls_keyfile: null\n",
"shields:\n",
"- params: null\n",
" provider_id: null\n",
" provider_shield_id: null\n",
" shield_id: meta-llama/Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8B\n",
"tool_groups:\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: tavily-search\n",
" toolgroup_id: builtin::websearch\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: rag-runtime\n",
" toolgroup_id: builtin::rag\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: code-interpreter\n",
" toolgroup_id: builtin::code_interpreter\n",
"vector_dbs: <span style=\"font-weight: bold\">[]</span>\n",
"version: <span style=\"color: #008000; text-decoration-color: #008000\">'2'</span>\n",
"\n",
"</pre>\n"
],
"text/plain": [
"apis:\n",
"- agents\n",
"- datasetio\n",
"- eval\n",
"- inference\n",
"- safety\n",
"- scoring\n",
"- telemetry\n",
"- tool_runtime\n",
"- vector_io\n",
"benchmarks: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
"container_image: null\n",
"datasets: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
"image_name: fireworks\n",
"metadata_store:\n",
" db_path: \u001b[35m/Users/xiyan/.llama/distributions/fireworks/\u001b[0m\u001b[95mregistry.db\u001b[0m\n",
" namespace: null\n",
" type: sqlite\n",
"models:\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-v3p1-8b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.1\u001b[0m-8B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-v3p1-70b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.1\u001b[0m-70B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-v3p1-405b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.1\u001b[0m-405B-Instruct-FP8\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-v3p2-1b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-1B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-1b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-v3p2-3b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-3B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-11B-Vision-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-90B-Vision-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-v3p3-70b-instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.3\u001b[0m-70B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-guard-\u001b[1;36m3\u001b[0m-8b\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-guard-\u001b[1;36m3\u001b[0m-8b\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-Guard-\u001b[1;36m3\u001b[0m-8B\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-guard-\u001b[1;36m3\u001b[0m-8b\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: accounts/fireworks/models/llama-guard-\u001b[1;36m3\u001b[0m-11b-vision\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-guard-\u001b[1;36m3\u001b[0m-11b-vision\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-Guard-\u001b[1;36m3\u001b[0m-11B-Vision\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: fireworks\n",
" provider_model_id: accounts/fireworks/models/llama-guard-\u001b[1;36m3\u001b[0m-11b-vision\n",
"- metadata:\n",
" context_length: \u001b[1;36m8192\u001b[0m\n",
" embedding_dimension: \u001b[1;36m768\u001b[0m\n",
" model_id: nomic-ai/nomic-embed-text-v1.\u001b[1;36m5\u001b[0m\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - embedding\n",
" provider_id: fireworks\n",
" provider_model_id: nomic-ai/nomic-embed-text-v1.\u001b[1;36m5\u001b[0m\n",
"- metadata:\n",
" embedding_dimension: \u001b[1;36m384\u001b[0m\n",
" model_id: all-MiniLM-L6-v2\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - embedding\n",
" provider_id: sentence-transformers\n",
" provider_model_id: null\n",
"providers:\n",
" agents:\n",
" - config:\n",
" persistence_store:\n",
" db_path: \u001b[35m/Users/xiyan/.llama/distributions/fireworks/\u001b[0m\u001b[95magents_store.db\u001b[0m\n",
" namespace: null\n",
" type: sqlite\n",
" provider_id: meta-reference\n",
" provider_type: inline::meta-reference\n",
" datasetio:\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: huggingface\n",
" provider_type: remote::huggingface\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: localfs\n",
" provider_type: inline::localfs\n",
" eval:\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: meta-reference\n",
" provider_type: inline::meta-reference\n",
" inference:\n",
" - config:\n",
" api_key: \u001b[32m'********'\u001b[0m\n",
" url: \u001b[4;94mhttps://api.fireworks.ai/inference/v1\u001b[0m\n",
" provider_id: fireworks\n",
" provider_type: remot\u001b[1;92me::f\u001b[0mireworks\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: sentence-transformers\n",
" provider_type: inline::sentence-transformers\n",
" safety:\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: llama-guard\n",
" provider_type: inline::llama-guard\n",
" scoring:\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: basic\n",
" provider_type: inlin\u001b[1;92me::ba\u001b[0msic\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: llm-as-judge\n",
" provider_type: inline::llm-as-judge\n",
" - config:\n",
" openai_api_key: \u001b[32m'********'\u001b[0m\n",
" provider_id: braintrust\n",
" provider_type: inlin\u001b[1;92me::b\u001b[0mraintrust\n",
" telemetry:\n",
" - config:\n",
" service_name: llama-stack\n",
" sinks: sqlite\n",
" sqlite_db_path: \u001b[35m/Users/xiyan/.llama/distributions/fireworks/\u001b[0m\u001b[95mtrace_store.db\u001b[0m\n",
" provider_id: meta-reference\n",
" provider_type: inline::meta-reference\n",
" tool_runtime:\n",
" - config:\n",
" api_key: \u001b[32m'********'\u001b[0m\n",
" max_results: \u001b[1;36m3\u001b[0m\n",
" provider_id: brave-search\n",
" provider_type: remot\u001b[1;92me::b\u001b[0mrave-search\n",
" - config:\n",
" api_key: \u001b[32m'********'\u001b[0m\n",
" max_results: \u001b[1;36m3\u001b[0m\n",
" provider_id: tavily-search\n",
" provider_type: remote::tavily-search\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: code-interpreter\n",
" provider_type: inlin\u001b[1;92me::c\u001b[0mode-interpreter\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: rag-runtime\n",
" provider_type: inline::rag-runtime\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: model-context-protocol\n",
" provider_type: remote::model-context-protocol\n",
" vector_io:\n",
" - config:\n",
" kvstore:\n",
" db_path: \u001b[35m/Users/xiyan/.llama/distributions/fireworks/\u001b[0m\u001b[95mfaiss_store.db\u001b[0m\n",
" namespace: null\n",
" type: sqlite\n",
" provider_id: faiss\n",
" provider_type: inlin\u001b[1;92me::fa\u001b[0miss\n",
"scoring_fns: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
"server:\n",
" port: \u001b[1;36m8321\u001b[0m\n",
" tls_certfile: null\n",
" tls_keyfile: null\n",
"shields:\n",
"- params: null\n",
" provider_id: null\n",
" provider_shield_id: null\n",
" shield_id: meta-llama/Llama-Guard-\u001b[1;36m3\u001b[0m-8B\n",
"tool_groups:\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: tavily-search\n",
" toolgroup_id: builtin::websearch\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: rag-runtime\n",
" toolgroup_id: builtin::rag\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: code-interpreter\n",
" toolgroup_id: builtin::code_interpreter\n",
"vector_dbs: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
"version: \u001b[32m'2'\u001b[0m\n",
"\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [ "source": [
"from llama_stack_client import LlamaStackClient\n", "from llama_stack_client import LlamaStackClient\n",
"from llama_stack.distribution.library_client import LlamaStackAsLibraryClient\n", "from llama_stack.distribution.library_client import LlamaStackAsLibraryClient\n",
@ -57,22 +614,12 @@
"from pydantic import BaseModel\n", "from pydantic import BaseModel\n",
"import rich\n", "import rich\n",
"import os\n", "import os\n",
"\n",
"try:\n", "try:\n",
" from google.colab import userdata\n", " from google.colab import userdata\n",
" os.environ['FIREWORKS_API_KEY'] = userdata.get('FIREWORKS_API_KEY')\n", " os.environ['FIREWORKS_API_KEY'] = userdata.get('FIREWORKS_API_KEY')\n",
"except ImportError:\n", "except ImportError:\n",
" print(\"Not in Google Colab environment\")\n", " print(\"Not in Google Colab environment\")\n",
"\n", "\n",
"for key in ['FIREWORKS_API_KEY']:\n",
" try:\n",
" api_key = os.environ[key]\n",
" if not api_key:\n",
" raise ValueError(f\"{key} environment variable is empty\")\n",
" except KeyError:\n",
" api_key = input(f\"{key} environment variable is not set. Please enter your API key: \")\n",
" os.environ[key] = api_key\n",
"\n",
"client = LlamaStackAsLibraryClient(\"fireworks\", provider_data = {\"fireworks_api_key\": os.environ['FIREWORKS_API_KEY']})\n", "client = LlamaStackAsLibraryClient(\"fireworks\", provider_data = {\"fireworks_api_key\": os.environ['FIREWORKS_API_KEY']})\n",
"_ = client.initialize()\n", "_ = client.initialize()\n",
"\n", "\n",
@ -1569,7 +2116,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 55, "execution_count": 110,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -1670,7 +2217,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 113,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -1680,22 +2227,25 @@
"```python\n", "```python\n",
"class MinStack:\n", "class MinStack:\n",
" def __init__(self):\n", " def __init__(self):\n",
" self.main_stack = []\n", " self.stack = []\n",
" self.min_stack = []\n", " self.min_stack = []\n",
"\n", " \n",
" def push(self, x: int) -> None:\n", " def push(self, x: int) -> None:\n",
" self.main_stack.append(x)\n", " self.stack.append(x)\n",
" if not self.min_stack or x <= self.min_stack[-1]:\n", " if not self.min_stack or x <= self.min_stack[-1]:\n",
" self.min_stack.append(x)\n", " self.min_stack.append(x)\n",
"\n", " \n",
" def pop(self) -> None:\n", " def pop(self) -> None:\n",
" if self.main_stack:\n", " if self.stack:\n",
" if self.main_stack[-1] == self.min_stack[-1]:\n", " if self.stack[-1] == self.min_stack[-1]:\n",
" self.min_stack.pop()\n", " self.min_stack.pop()\n",
" self.main_stack.pop()\n", " self.stack.pop()\n",
"\n", " \n",
" def getMin(self) -> int:\n", " def getMin(self) -> int:\n",
" return self.min_stack[-1]\n", " if self.min_stack:\n",
" return self.min_stack[-1]\n",
" else:\n",
" return None\n",
"```\n" "```\n"
] ]
} }
@ -1709,7 +2259,8 @@
"All operations should be O(1).\n", "All operations should be O(1).\n",
"\"\"\"\n", "\"\"\"\n",
"\n", "\n",
"print(generator_evaluator_workflow(coding_task)[\"response\"])" "output = generator_evaluator_workflow(coding_task)\n",
"print(output[\"response\"])"
] ]
}, },
{ {