diff --git a/llama_stack/distributions/dell/run.yaml b/llama_stack/distributions/dell/run.yaml index fc2553526..2bbe56057 100644 --- a/llama_stack/distributions/dell/run.yaml +++ b/llama_stack/distributions/dell/run.yaml @@ -23,6 +23,9 @@ providers: provider_type: remote::chromadb config: url: ${env.CHROMA_URL} + kvstore: + type: sqlite + db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter/}/chroma_remote_registry.db safety: - provider_id: llama-guard provider_type: inline::llama-guard diff --git a/llama_stack/providers/remote/inference/tgi/tgi.py b/llama_stack/providers/remote/inference/tgi/tgi.py index a5bb079ef..34d2c9e7a 100644 --- a/llama_stack/providers/remote/inference/tgi/tgi.py +++ b/llama_stack/providers/remote/inference/tgi/tgi.py @@ -309,7 +309,7 @@ class TGIAdapter(_HfAdapter): raise ValueError("You must provide a URL in run.yaml (or via the TGI_URL environment variable) to use TGI.") log.info(f"Initializing TGI client with url={config.url}") self.client = AsyncInferenceClient( - model=config.url, + model=config.url,provider="hf-inference" ) endpoint_info = await self.client.get_endpoint_info() self.max_tokens = endpoint_info["max_total_tokens"]