From ec8abe1c7832532c90c0662982966d0ee3b1faed Mon Sep 17 00:00:00 2001 From: Ashwin Bharambe Date: Fri, 21 Feb 2025 10:31:33 -0800 Subject: [PATCH] update the template properly --- distributions/dependencies.json | 1 + docs/source/distributions/self_hosted_distro/ollama.md | 2 +- llama_stack/templates/ollama/ollama.py | 2 +- 3 files changed, 3 insertions(+), 2 deletions(-) diff --git a/distributions/dependencies.json b/distributions/dependencies.json index 345a29f33..df63c0773 100644 --- a/distributions/dependencies.json +++ b/distributions/dependencies.json @@ -356,6 +356,7 @@ "scikit-learn", "scipy", "sentencepiece", + "sqlite-vec", "tqdm", "transformers", "uvicorn", diff --git a/docs/source/distributions/self_hosted_distro/ollama.md b/docs/source/distributions/self_hosted_distro/ollama.md index 2fa796e81..b800b4a43 100644 --- a/docs/source/distributions/self_hosted_distro/ollama.md +++ b/docs/source/distributions/self_hosted_distro/ollama.md @@ -23,7 +23,7 @@ The `llamastack/distribution-ollama` distribution consists of the following prov | scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` | | telemetry | `inline::meta-reference` | | tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime` | -| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` | +| vector_io | `inline::faiss`, `inline::sqlite_vec`, `remote::chromadb`, `remote::pgvector` | You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration. diff --git a/llama_stack/templates/ollama/ollama.py b/llama_stack/templates/ollama/ollama.py index 31119e040..2b135c008 100644 --- a/llama_stack/templates/ollama/ollama.py +++ b/llama_stack/templates/ollama/ollama.py @@ -25,7 +25,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin def get_distribution_template() -> DistributionTemplate: providers = { "inference": ["remote::ollama"], - "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"], + "vector_io": ["inline::faiss", "inline::sqlite_vec", "remote::chromadb", "remote::pgvector"], "safety": ["inline::llama-guard"], "agents": ["inline::meta-reference"], "telemetry": ["inline::meta-reference"],