fix after rebasing, now test isn't working

meta-llama · Feb 4, 2025 · 3a224f5 · 3a224f5
1 parent f9f9101
commit 3a224f5
Show file tree

Hide file tree

Showing 4 changed files with 30 additions and 14 deletions.
diff --git a/llama_stack/providers/registry/inference.py b/llama_stack/providers/registry/inference.py
@@ -216,15 +216,23 @@ def available_providers() -> List[ProviderSpec]:
         remote_provider_spec(
             api=Api.inference,
             adapter=AdapterSpec(
-                adapter_type="centml",
+                adapter_type="runpod",
+                pip_packages=["openai"],
+                module="llama_stack.providers.remote.inference.runpod",
+                config_class=
+                "llama_stack.providers.remote.inference.runpod.RunpodImplConfig",
+            ),
+        ),
+        remote_provider_spec(
+            api=Api.inference,
+            adapter=AdapterSpec(
+                adapter_type="sambanova",
                 pip_packages=[
                     "openai",
                 ],
-                module="llama_stack.providers.remote.inference.centml",
+                module="llama_stack.providers.remote.inference.sambanova",
                 config_class=
-                "llama_stack.providers.remote.inference.centml.CentMLImplConfig",
-                provider_data_validator=
-                "llama_stack.providers.remote.inference.centml.CentMLProviderDataValidator",
+                "llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
             ),
         ),
         remote_provider_spec(

diff --git a/llama_stack/providers/remote/inference/centml/centml.py b/llama_stack/providers/remote/inference/centml/centml.py
@@ -17,6 +17,7 @@
     ChatCompletionRequest,
     ChatCompletionResponse,
     CompletionRequest,
+    CompletionResponse,
     EmbeddingsResponse,
     Inference,
     LogProbConfig,
@@ -25,6 +26,7 @@
     ResponseFormatType,
     SamplingParams,
     ToolChoice,
+    ToolConfig,
     ToolDefinition,
     ToolPromptFormat,
 )
@@ -42,6 +44,7 @@
     process_completion_stream_response,
 )
 from llama_stack.providers.utils.inference.prompt_adapter import (
+    chat_completion_request_to_prompt,
     completion_request_to_prompt,
     content_has_media,
     interleaved_content_as_str,
@@ -176,6 +179,7 @@ async def chat_completion(
         response_format: Optional[ResponseFormat] = None,
         stream: Optional[bool] = False,
         logprobs: Optional[LogProbConfig] = None,
+        tool_config: Optional[ToolConfig] = None,
     ) -> AsyncGenerator:
         """
         For "chat completion" style requests.

diff --git a/llama_stack/templates/centml/build.yaml b/llama_stack/templates/centml/build.yaml
@@ -5,7 +5,7 @@ distribution_spec:
   providers:
     inference:
     - remote::centml
-    memory:
+    vector_io:
     - inline::faiss
     - remote::chromadb
     - remote::pgvector
@@ -28,5 +28,6 @@ distribution_spec:
     - remote::brave-search
     - remote::tavily-search
     - inline::code-interpreter
-    - inline::memory-runtime
+    - inline::rag-runtime
+    - remote::model-context-protocol
 image_type: conda
diff --git a/llama_stack/templates/centml/run.yaml b/llama_stack/templates/centml/run.yaml
@@ -6,11 +6,11 @@ apis:
   - datasetio
   - eval
   - inference
-  - memory
   - safety
   - scoring
   - telemetry
   - tool_runtime
+  - vector_io
 providers:
   inference:
   - provider_id: centml
@@ -22,7 +22,7 @@ providers:
     provider_type: inline::sentence-transformers
     config: {}
 
-  memory:
+  vector_io:
   - provider_id: faiss
     provider_type: inline::faiss
     config:
@@ -92,8 +92,11 @@ providers:
   - provider_id: code-interpreter
     provider_type: inline::code-interpreter
     config: {}
-  - provider_id: memory-runtime
-    provider_type: inline::memory-runtime
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+    config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
     config: {}
 
 metadata_store:
@@ -116,14 +119,14 @@ models:
 shields:
   - shield_id: meta-llama/Llama-Guard-3-8B
 
-memory_banks: []
+vector_dbs: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
 tool_groups:
   - toolgroup_id: builtin::websearch
     provider_id: tavily-search
-  - toolgroup_id: builtin::memory
-    provider_id: memory-runtime
+  - toolgroup_id: builtin::rag
+    provider_id: rag-runtime
   - toolgroup_id: builtin::code_interpreter
     provider_id: code-interpreter