use logging instead of prints (#499)

# What does this PR do?

This PR moves all print statements to use logging. Things changed:
- Had to add `await start_trace("sse_generator")` to server.py to
actually get tracing working. else was not seeing any logs
- If no telemetry provider is provided in the run.yaml, we will write to
stdout
- by default, the logs are going to be in JSON, but we expose an option
to configure to output in a human readable way.

llama_stack/providers/remote/inference/ollama/ollama.py

@@ -4,6 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+import logging
 from typing import AsyncGenerator
 
 import httpx
@@ -39,6 +40,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
     request_has_media,
 )
 
+log = logging.getLogger(__name__)
 
 model_aliases = [
     build_model_alias(
@@ -105,7 +107,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
         return AsyncClient(host=self.url)
 
     async def initialize(self) -> None:
-        print(f"checking connectivity to Ollama at `{self.url}`...")
+        log.info(f"checking connectivity to Ollama at `{self.url}`...")
         try:
             await self.client.ps()
         except httpx.ConnectError as e:

llama_stack/providers/remote/inference/tgi/tgi.py

@@ -34,7 +34,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 
 from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
 
-logger = logging.getLogger(__name__)
+log = logging.getLogger(__name__)
 
 
 class _HfAdapter(Inference, ModelsProtocolPrivate):
@@ -264,7 +264,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
 
 class TGIAdapter(_HfAdapter):
     async def initialize(self, config: TGIImplConfig) -> None:
-        print(f"Initializing TGI client with url={config.url}")
+        log.info(f"Initializing TGI client with url={config.url}")
         self.client = AsyncInferenceClient(model=config.url, token=config.api_token)
         endpoint_info = await self.client.get_endpoint_info()
         self.max_tokens = endpoint_info["max_total_tokens"]

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -3,6 +3,8 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
+
+import logging
 from typing import AsyncGenerator
 
 from llama_models.llama3.api.chat_format import ChatFormat
@@ -34,6 +36,9 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
 from .config import VLLMInferenceAdapterConfig
 
 
+log = logging.getLogger(__name__)
+
+
 def build_model_aliases():
     return [
         build_model_alias(
@@ -53,7 +58,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
         self.client = None
 
     async def initialize(self) -> None:
-        print(f"Initializing VLLM client with base_url={self.config.url}")
+        log.info(f"Initializing VLLM client with base_url={self.config.url}")
         self.client = OpenAI(base_url=self.config.url, api_key=self.config.api_token)
 
     async def shutdown(self) -> None:

llama_stack/providers/remote/memory/chroma/chroma.py

@@ -5,6 +5,7 @@
 # the root directory of this source tree.
 
 import json
+import logging
 from typing import List
 from urllib.parse import urlparse
 
@@ -21,6 +22,8 @@ from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
 )
 
+log = logging.getLogger(__name__)
+
 
 class ChromaIndex(EmbeddingIndex):
     def __init__(self, client: chromadb.AsyncHttpClient, collection):
@@ -56,10 +59,7 @@ class ChromaIndex(EmbeddingIndex):
                 doc = json.loads(doc)
                 chunk = Chunk(**doc)
             except Exception:
-                import traceback
-
-                traceback.print_exc()
-                print(f"Failed to parse document: {doc}")
+                log.exception(f"Failed to parse document: {doc}")
                 continue
 
             chunks.append(chunk)
@@ -73,7 +73,7 @@ class ChromaIndex(EmbeddingIndex):
 
 class ChromaMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
     def __init__(self, url: str) -> None:
-        print(f"Initializing ChromaMemoryAdapter with url: {url}")
+        log.info(f"Initializing ChromaMemoryAdapter with url: {url}")
         url = url.rstrip("/")
         parsed = urlparse(url)
 
@@ -88,12 +88,10 @@ class ChromaMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
 
     async def initialize(self) -> None:
         try:
-            print(f"Connecting to Chroma server at: {self.host}:{self.port}")
+            log.info(f"Connecting to Chroma server at: {self.host}:{self.port}")
             self.client = await chromadb.AsyncHttpClient(host=self.host, port=self.port)
         except Exception as e:
-            import traceback
-
-            traceback.print_exc()
+            log.exception("Could not connect to Chroma server")
             raise RuntimeError("Could not connect to Chroma server") from e
 
     async def shutdown(self) -> None:
@@ -123,10 +121,7 @@ class ChromaMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
                 data = json.loads(collection.metadata["bank"])
                 bank = parse_obj_as(VectorMemoryBank, data)
             except Exception:
-                import traceback
-
-                traceback.print_exc()
-                print(f"Failed to parse bank: {collection.metadata}")
+                log.exception(f"Failed to parse bank: {collection.metadata}")
                 continue
 
             index = BankWithIndex(

llama_stack/providers/remote/memory/pgvector/pgvector.py

@@ -4,6 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+import logging
 from typing import List, Tuple
 
 import psycopg2
@@ -24,6 +25,8 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import PGVectorConfig
 
+log = logging.getLogger(__name__)
+
 
 def check_extension_version(cur):
     cur.execute("SELECT extversion FROM pg_extension WHERE extname = 'vector'")
@@ -124,7 +127,7 @@ class PGVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
         self.cache = {}
 
     async def initialize(self) -> None:
-        print(f"Initializing PGVector memory adapter with config: {self.config}")
+        log.info(f"Initializing PGVector memory adapter with config: {self.config}")
         try:
             self.conn = psycopg2.connect(
                 host=self.config.host,
@@ -138,7 +141,7 @@ class PGVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
 
             version = check_extension_version(self.cursor)
             if version:
-                print(f"Vector extension version: {version}")
+                log.info(f"Vector extension version: {version}")
             else:
                 raise RuntimeError("Vector extension is not installed.")
 
@@ -151,9 +154,7 @@ class PGVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
             """
             )
         except Exception as e:
-            import traceback
-
-            traceback.print_exc()
+            log.exception("Could not connect to PGVector database server")
             raise RuntimeError("Could not connect to PGVector database server") from e
 
     async def shutdown(self) -> None:

llama_stack/providers/remote/memory/qdrant/qdrant.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import traceback
+import logging
 import uuid
 from typing import Any, Dict, List
 
@@ -23,6 +23,7 @@ from llama_stack.providers.utils.memory.vector_store import (
     EmbeddingIndex,
 )
 
+log = logging.getLogger(__name__)
 CHUNK_ID_KEY = "_chunk_id"
 
 
@@ -90,7 +91,7 @@ class QdrantIndex(EmbeddingIndex):
             try:
                 chunk = Chunk(**point.payload["chunk_content"])
             except Exception:
-                traceback.print_exc()
+                log.exception("Failed to parse chunk")
                 continue
 
             chunks.append(chunk)

llama_stack/providers/remote/memory/weaviate/weaviate.py

@@ -4,6 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 import json
+import logging
 
 from typing import Any, Dict, List, Optional
 
@@ -22,6 +23,8 @@ from llama_stack.providers.utils.memory.vector_store import (
 
 from .config import WeaviateConfig, WeaviateRequestProviderData
 
+log = logging.getLogger(__name__)
+
 
 class WeaviateIndex(EmbeddingIndex):
     def __init__(self, client: weaviate.Client, collection_name: str):
@@ -69,10 +72,7 @@ class WeaviateIndex(EmbeddingIndex):
                 chunk_dict = json.loads(chunk_json)
                 chunk = Chunk(**chunk_dict)
             except Exception:
-                import traceback
-
-                traceback.print_exc()
-                print(f"Failed to parse document: {chunk_json}")
+                log.exception(f"Failed to parse document: {chunk_json}")
                 continue
 
             chunks.append(chunk)