fix: revert to using faiss for ollama distro (#1530)

This is unfortunate because `sqlite-vec` seems promising. But its PIP
package is not quite complete. It does not have binary for arm64 (I
think, or maybe it even lacks 64 bit builds?) which results in the arm64
container resulting in
```
File "/usr/local/lib/python3.10/site-packages/sqlite_vec/init.py", line 17, in load
    conn.load_extension(loadable_path())
sqlite3.OperationalError: /usr/local/lib/python3.10/site-packages/sqlite_vec/vec0.so: wrong ELF class: ELFCLASS32
```

To get around I tried to install from source via `uv pip install
sqlite-vec --no-binary=sqlite-vec` however it even lacks a source
distribution which makes that impossible.

## Test Plan

Build the container locally using: 

```bash
LLAMA_STACK_DIR=. llama stack build --template ollama --image-type container
```

Run the container as: 

```
podman run --privileged -it -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ~/.llama:/root/.llama \
    --env INFERENCE_MODEL=$INFERENCE_MODEL \
    --env OLLAMA_URL=http://host.containers.internal:11434 \
    -v ~/local/llama-stack:/app/llama-stack-source 
    localhost/distribution-ollama:dev --port $LLAMA_STACK_PORT
```

Verify the container starts up correctly. Without this patch, it would
encounter the ELFCLASS32 error.

distributions/dependencies.json

@@ -427,6 +427,7 @@
     "chardet",
     "chromadb-client",
     "datasets",
+    "faiss-cpu",
     "fastapi",
     "fire",
     "httpx",
@@ -448,7 +449,6 @@
     "scikit-learn",
     "scipy",
     "sentencepiece",
-    "sqlite-vec",
     "tqdm",
     "transformers",
     "uvicorn"

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`, `remote::model-context-protocol`, `remote::wolfram-alpha` |
-| vector_io | `inline::sqlite-vec`, `remote::chromadb`, `remote::pgvector` |
+| vector_io | `inline::faiss`, `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.

llama_stack/providers/registry/vector_io.py

@@ -34,6 +34,8 @@ def available_providers() -> List[ProviderSpec]:
             config_class="llama_stack.providers.inline.vector_io.faiss.FaissVectorIOConfig",
             api_dependencies=[Api.inference],
         ),
+        # NOTE: sqlite-vec cannot be bundled into the container image because it does not have a
+        # source distribution and the wheels are not available for all platforms.
         InlineProviderSpec(
             api=Api.vector_io,
             provider_type="inline::sqlite-vec",

llama_stack/templates/ollama/build.yaml

@@ -5,7 +5,7 @@ distribution_spec:
     inference:
     - remote::ollama
     vector_io:
-    - inline::sqlite-vec
+    - inline::faiss
     - remote::chromadb
     - remote::pgvector
     safety:

llama_stack/templates/ollama/ollama.py

@@ -13,7 +13,7 @@ from llama_stack.distribution.datatypes import (
     ShieldInput,
     ToolGroupInput,
 )
-from llama_stack.providers.inline.vector_io.sqlite_vec.config import SQLiteVectorIOConfig
+from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
 from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
 from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
 
@@ -21,7 +21,7 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::ollama"],
-        "vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
+        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
         "safety": ["inline::llama-guard"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
@@ -43,10 +43,10 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="remote::ollama",
         config=OllamaImplConfig.sample_run_config(),
     )
-    vector_io_provider_sqlite = Provider(
-        provider_id="sqlite-vec",
-        provider_type="inline::sqlite-vec",
-        config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+    vector_io_provider_faiss = Provider(
+        provider_id="faiss",
+        provider_type="inline::faiss",
+        config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
     )
 
     inference_model = ModelInput(
@@ -96,7 +96,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider],
-                    "vector_io": [vector_io_provider_sqlite],
+                    "vector_io": [vector_io_provider_faiss],
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
@@ -104,7 +104,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider],
-                    "vector_io": [vector_io_provider_sqlite],
+                    "vector_io": [vector_io_provider_faiss],
                     "safety": [
                         Provider(
                             provider_id="llama-guard",

llama_stack/templates/ollama/run-with-safety.yaml

@@ -17,10 +17,13 @@ providers:
     config:
       url: ${env.OLLAMA_URL:http://localhost:11434}
   vector_io:
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
+  - provider_id: faiss
+    provider_type: inline::faiss
     config:
-      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/sqlite_vec.db
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard

llama_stack/templates/ollama/run.yaml

@@ -17,10 +17,13 @@ providers:
     config:
       url: ${env.OLLAMA_URL:http://localhost:11434}
   vector_io:
-  - provider_id: sqlite-vec
-    provider_type: inline::sqlite-vec
+  - provider_id: faiss
+    provider_type: inline::faiss
     config:
-      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/sqlite_vec.db
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard