feat: Add synthetic-data-kit for file_search doc conversion

This adds a `builtin::document_conversion` tool for converting
documents when used with file_search that uses
meta-llama/synthetic-data-kit. I also have another local
implementation that uses Docling, but need to debug some segfault
issues I'm hitting locally with that so pushing this first as a
simpler reference implementation.

Long-term I think we'll want a remote implemention here as well - like
perhaps docling-serve or unstructured.io - but need to look more into
that.

This passes the existing
`tests/verifications/openai_api/test_responses.py` but doesn't yet add
any new tests for file types besides text and pdf.

Signed-off-by: Ben Browning <bbrownin@redhat.com>

llama_stack/templates/ollama/build.yaml

@@ -31,6 +31,7 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::rag-runtime
+    - inline::synthetic-data-kit
     - remote::model-context-protocol
     - remote::wolfram-alpha
 image_type: conda

llama_stack/templates/ollama/ollama.py

@@ -36,6 +36,7 @@ def get_distribution_template() -> DistributionTemplate:
             "remote::brave-search",
             "remote::tavily-search",
             "inline::rag-runtime",
+            "inline::synthetic-data-kit",
             "remote::model-context-protocol",
             "remote::wolfram-alpha",
         ],
@@ -91,6 +92,10 @@ def get_distribution_template() -> DistributionTemplate:
             toolgroup_id="builtin::wolfram_alpha",
             provider_id="wolfram-alpha",
         ),
+        ToolGroupInput(
+            toolgroup_id="builtin::document_conversion",
+            provider_id="synthetic-data-kit",
+        ),
     ]
 
     return DistributionTemplate(

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

@@ -115,6 +115,9 @@ providers:
   - provider_id: rag-runtime
     provider_type: inline::rag-runtime
     config: {}
+  - provider_id: synthetic-data-kit
+    provider_type: inline::synthetic-data-kit
+    config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
     config: {}
@@ -159,5 +162,7 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::wolfram_alpha
   provider_id: wolfram-alpha
+- toolgroup_id: builtin::document_conversion
+  provider_id: synthetic-data-kit
 server:
   port: 8321

llama_stack/templates/ollama/run.yaml

@@ -113,6 +113,9 @@ providers:
   - provider_id: rag-runtime
     provider_type: inline::rag-runtime
     config: {}
+  - provider_id: synthetic-data-kit
+    provider_type: inline::synthetic-data-kit
+    config: {}
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
     config: {}
@@ -149,5 +152,7 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::wolfram_alpha
   provider_id: wolfram-alpha
+- toolgroup_id: builtin::document_conversion
+  provider_id: synthetic-data-kit
 server:
   port: 8321