From 44fe09986620952cbbf07fb28b088c7cc5c2a29a Mon Sep 17 00:00:00 2001 From: Xi Yan Date: Sun, 22 Sep 2024 00:25:01 -0700 Subject: [PATCH] update example run files --- llama_stack/examples/router-local-run.yaml | 50 ++++++++++++++++ llama_stack/examples/router-table-run.yaml | 67 ---------------------- llama_stack/examples/simple-local-run.yaml | 5 +- 3 files changed, 51 insertions(+), 71 deletions(-) create mode 100644 llama_stack/examples/router-local-run.yaml delete mode 100644 llama_stack/examples/router-table-run.yaml diff --git a/llama_stack/examples/router-local-run.yaml b/llama_stack/examples/router-local-run.yaml new file mode 100644 index 000000000..08cf9a804 --- /dev/null +++ b/llama_stack/examples/router-local-run.yaml @@ -0,0 +1,50 @@ +built_at: '2024-09-18T13:41:17.656743' +image_name: local +docker_image: null +conda_env: local +apis_to_serve: +- inference +- memory +- telemetry +- agents +- safety +- models +provider_map: + telemetry: + provider_id: meta-reference + config: {} + safety: + provider_id: meta-reference + config: + llama_guard_shield: + model: Llama-Guard-3-8B + excluded_categories: [] + disable_input_check: false + disable_output_check: false + prompt_guard_shield: + model: Prompt-Guard-86M + agents: + provider_id: meta-reference + config: {} +provider_routing_table: + inference: + - routing_key: Meta-Llama3.1-8B-Instruct + provider_id: meta-reference + config: + model: Meta-Llama3.1-8B-Instruct + quantization: null + torch_seed: null + max_seq_len: 4096 + max_batch_size: 1 + - routing_key: Meta-Llama3.1-8B + provider_id: meta-reference + config: + model: Meta-Llama3.1-8B + quantization: null + torch_seed: null + max_seq_len: 4096 + max_batch_size: 1 + memory: + - routing_key: vector + provider_id: meta-reference + config: {} diff --git a/llama_stack/examples/router-table-run.yaml b/llama_stack/examples/router-table-run.yaml deleted file mode 100644 index d3287eb38..000000000 --- a/llama_stack/examples/router-table-run.yaml +++ /dev/null @@ -1,67 +0,0 @@ -built_at: '2024-09-18T13:41:17.656743' -image_name: local -docker_image: null -conda_env: local -apis_to_serve: -- inference -# - memory -- telemetry -# - agents -# - safety -- models -provider_map: - telemetry: - provider_id: meta-reference - config: {} - # safety: - # provider_id: meta-reference - # config: - # llama_guard_shield: - # model: Llama-Guard-3-8B - # excluded_categories: [] - # disable_input_check: false - # disable_output_check: false - # prompt_guard_shield: - # model: Prompt-Guard-86M - # inference: - # provider_id: meta-reference - # config: - # model: Meta-Llama3.1-8B-Instruct - # quantization: null - # torch_seed: null - # max_seq_len: 4096 - # max_batch_size: 1 - # inference: - # provider_id: remote::ollama - # config: - # url: https:ollama-1.com - # agents: - # provider_id: meta-reference - # config: {} -provider_routing_table: - inference: - - routing_key: Meta-Llama3.1-8B-Instruct - provider_id: meta-reference - config: - model: Meta-Llama3.1-8B-Instruct - quantization: null - torch_seed: null - max_seq_len: 4096 - max_batch_size: 1 - - routing_key: Meta-Llama3.1-8B - provider_id: remote::ollama - config: - url: https:://ollama.com - - # memory: - # - routing_key: keyvalue - # provider_id: remote::pgvector - # config: - # host: localhost - # port: 5432 - # db: vectordb - # user: vectoruser - # password: xxxx - # - routing_key: vector - # provider_id: meta-reference - # config: {} diff --git a/llama_stack/examples/simple-local-run.yaml b/llama_stack/examples/simple-local-run.yaml index b628894c1..f517116aa 100644 --- a/llama_stack/examples/simple-local-run.yaml +++ b/llama_stack/examples/simple-local-run.yaml @@ -8,6 +8,7 @@ apis_to_serve: - agents - memory - models +- telemetry provider_map: inference: provider_id: meta-reference @@ -17,10 +18,6 @@ provider_map: torch_seed: null max_seq_len: 4096 max_batch_size: 1 - # inference: - # provider_id: remote::ollama - # config: - # url: https://xxx safety: provider_id: meta-reference config: