Refactor logging implementation and remove logfire dependency

- Replaced logfire logging with standard Python logging across multiple scripts for improved consistency and maintainability.
- Updated AGENTS.md to clarify agent tracing and server logging practices.
- Removed logfire from dependencies in pyproject.toml and uv.lock, streamlining the project setup.
- Enhanced logging messages for better clarity and context in various components, including api.py, chat_service.py, and setup.py.

AGENTS.md

@@ -29,7 +29,7 @@ ChromaDB for vectors; Cohere for embeddings/rerank; chat model is provider-confi
 | Gradio app + renderer | `scripts/main.py`, `scripts/gradio_presenter.py` |
 | Paths, models, startup downloads | `scripts/setup.py` |
 | **Sources — single source of truth** | `data/scraping_scripts/source_registry.py` |
-| Tracing (LangSmith + Logfire) | `scripts/agent_tracing.py`, `scripts/setup.py` |
+| Agent tracing (LangSmith) + server logging (stdlib `logging` → stdout) | `scripts/agent_tracing.py`, `scripts/setup.py` |
 | Data pipeline / workflows (deep guide) | `data/scraping_scripts/README.md` |
 | KB design + wiki maintainer workflow (deep guide) | `data/kb/MAINTAINER.md` |
 

pyproject.toml

@@ -20,7 +20,6 @@ dependencies = [
     "langchain-google-genai",
     "langchain-openai",
     "llama-index",
-    "logfire",
     "nbconvert",
     "nbformat",
     "openai",

scripts/api.py

@@ -1,13 +1,13 @@
 from __future__ import annotations
 
 import json
+import logging
 import os
 from contextlib import asynccontextmanager
 from pathlib import Path
 from typing import Any, AsyncIterator
 from uuid import uuid4
 
-import logfire
 import uvicorn
 from fastapi import FastAPI, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
@@ -34,6 +34,8 @@ from .setup import (
     SOURCE_UI_TO_KEY,
 )
 
+logger = logging.getLogger(__name__)
+
 
 class ApiChatTurn(BaseModel):
     role: str
@@ -486,9 +488,9 @@ if FRONTEND_OUT_DIR.is_dir():
         name="frontend",
     )
 else:
-    logfire.info(
-        "Frontend static export not found; skipping static mount.",
-        path=str(FRONTEND_OUT_DIR),
+    logger.info(
+        "Frontend static export not found; skipping static mount. path=%s",
+        FRONTEND_OUT_DIR,
     )
 
 

scripts/chat_service.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import json
+import logging
 import os
 import shlex
 from dataclasses import dataclass
@@ -9,7 +10,6 @@ from threading import Lock
 from typing import Any, AsyncIterator
 from uuid import uuid4
 
-import logfire
 from langchain.agents import create_agent
 from langchain.agents.middleware import (
     AgentMiddleware,
@@ -55,6 +55,8 @@ from .setup import (
     ensure_local_vector_db,
 )
 
+logger = logging.getLogger(__name__)
+
 SOURCES_HEADER = "📝 Here are the sources I used to answer your question:"
 ACTIVITY_BLOCK_START = "<!-- MODEL_ACTIVITY_START -->"
 ACTIVITY_BLOCK_END = "<!-- MODEL_ACTIVITY_END -->"
@@ -121,9 +123,9 @@ def warm_up_retriever() -> None:
     try:
         get_retriever()
     except Exception as exc:  # pragma: no cover - diagnostic logging only
-        logfire.warn(
-            "Retriever warm-up failed; first retrieval call may retry.",
-            error=str(exc),
+        logger.warning(
+            "Retriever warm-up failed; first retrieval call may retry. error=%s",
+            exc,
         )
 
 
@@ -201,7 +203,7 @@ def run_kb_command(
     try:
         ensure_local_vector_db()
     except Exception as exc:  # pragma: no cover - diagnostic only
-        logfire.warn("KB artifact download/check failed.", error=str(exc))
+        logger.warning("KB artifact download/check failed. error=%s", exc)
     try:
         result = execute_kb_command(
             command,
@@ -1046,7 +1048,7 @@ async def stream_chat(request: ChatRequest) -> AsyncIterator[ChatEvent]:
     google_search_queries: list[str] = []
     google_search_match_count = 0
 
-    logfire.info("Running query", query=request.query)
+    logger.info("Running query: %s", request.query)
     agent = build_agent(
         request.model_name,
         enabled_tools=tuple(request.enabled_tools),

scripts/chroma_rag.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import json
+import logging
 import math
 import os
 import pickle
@@ -16,10 +17,11 @@ from urllib.parse import unquote, urlparse
 
 import chromadb
 import cohere
-import logfire
 import tiktoken
 from tqdm.auto import tqdm
 
+logger = logging.getLogger(__name__)
+
 
 DEFAULT_CHUNK_SIZE = 800
 DEFAULT_CHUNK_OVERLAP = 100
@@ -1381,5 +1383,5 @@ def parse_tool_payload(content: str) -> list[SearchResult]:
         try:
             parsed.append(SearchResult(**match))
         except TypeError:
-            logfire.warn("Skipping malformed retrieval payload entry")
+            logger.warning("Skipping malformed retrieval payload entry")
     return parsed

scripts/setup.py

@@ -1,7 +1,7 @@
+import logging
 import os
 from pathlib import Path
 
-import logfire
 from dotenv import load_dotenv
 
 from data.scraping_scripts.source_registry import (
@@ -19,15 +19,21 @@ from .utils import init_mongo_db
 
 load_dotenv(override=True)
 configure_langsmith_environment()
-try:
-    logfire.configure()
-except Exception:
-    pass
+
+# Operational/server logging goes to stdout (captured by the Hugging Face Space
+# logs). This is separate from LangSmith, which traces agent runs; see
+# scripts/agent_tracing.py. basicConfig is a no-op if logging is already
+# configured (e.g. by a data-pipeline entry point), so it won't clobber callers.
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s %(levelname)s [%(name)s] %(message)s",
+)
+logger = logging.getLogger(__name__)
 
 if langsmith_tracing_enabled():
-    logfire.info(
-        "LangSmith tracing enabled.",
-        project=os.getenv("LANGSMITH_PROJECT", "default"),
+    logger.info(
+        "LangSmith tracing enabled. project=%s",
+        os.getenv("LANGSMITH_PROJECT", "default"),
     )
 
 VECTOR_DB_DIR = "data/chroma-db-all_sources"
@@ -69,7 +75,7 @@ def ensure_local_vector_db() -> None:
         and os.path.exists(KB_INDEX_PATH)
     )
     if needs_download:
-        logfire.warn(
+        logger.warning(
             "Vector database does not exist locally, downloading from Hugging Face"
         )
         from huggingface_hub import snapshot_download
@@ -82,11 +88,11 @@ def ensure_local_vector_db() -> None:
     ensure_kb_agents_md()
 
 
-mongo_db = (
-    init_mongo_db(uri=MONGODB_URI, db_name="towardsai-buster")
-    if MONGODB_URI
-    else logfire.warn("No mongodb uri found, you will not be able to save data.")
-)
+if MONGODB_URI:
+    mongo_db = init_mongo_db(uri=MONGODB_URI, db_name="towardsai-buster")
+else:
+    logger.warning("No mongodb uri found, you will not be able to save data.")
+    mongo_db = None
 
 __all__ = [
     "AVAILABLE_MODELS",

uv.lock

@@ -30,7 +30,6 @@ dependencies = [
     { name = "langchain-google-genai" },
     { name = "langchain-openai" },
     { name = "llama-index" },
-    { name = "logfire" },
     { name = "nbconvert" },
     { name = "nbformat" },
     { name = "openai" },
@@ -66,7 +65,6 @@ requires-dist = [
     { name = "langchain-google-genai" },
     { name = "langchain-openai" },
     { name = "llama-index" },
-    { name = "logfire" },
     { name = "nbconvert" },
     { name = "nbformat" },
     { name = "openai" },
@@ -1961,24 +1959,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/71/5f/385231406d777cb4b608fd8ebe3577dbd90962770717181e6b91b44fb1b8/llama_index_workflows-2.20.0-py3-none-any.whl", hash = "sha256:36f6b6ace77f837d9907078aea7e830251afe96a58daecff5ed090c88c55095d", size = 121238, upload-time = "2026-04-24T14:54:40.455Z" },
 ]
 
-[[package]]
-name = "logfire"
-version = "4.35.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "executing" },
-    { name = "opentelemetry-exporter-otlp-proto-http" },
-    { name = "opentelemetry-instrumentation" },
-    { name = "opentelemetry-sdk" },
-    { name = "protobuf" },
-    { name = "rich" },
-    { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/7c/20/9508c92ad4ec2ed4ad63a20d72f08427c24117273541ec97c630332855c3/logfire-4.35.0.tar.gz", hash = "sha256:6542aa4ac5e2d2369587deab57a0d1bb9cf6da49634c8cd9c5dbd7c7581f3d51", size = 1148150, upload-time = "2026-06-02T14:55:56.792Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/77/37/a3631d0b7e4fcb19df4705c7c7e17164c5446e144f034723cf6277749973/logfire-4.35.0-py3-none-any.whl", hash = "sha256:9ae5c3f2dd81144ccf1ec6dba1a5de84aff5b2e2b8dd2190e53e87e47bc63711", size = 347012, upload-time = "2026-06-02T14:55:53.244Z" },
-]
-
 [[package]]
 name = "markdown-it-py"
 version = "4.2.0"
@@ -2476,39 +2456,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/89/2b/28ba5b128f47fe8c3bab541000d6feb4b5a9bd26623ca013406f01c0fb60/opentelemetry_exporter_otlp_proto_grpc-1.42.1-py3-none-any.whl", hash = "sha256:0ae1177e2038b18a929b3098215243631ef91136cba26b7e2b12790ceb7e87cc", size = 19617, upload-time = "2026-05-21T16:32:34.278Z" },
 ]
 
-[[package]]
-name = "opentelemetry-exporter-otlp-proto-http"
-version = "1.42.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "googleapis-common-protos" },
-    { name = "opentelemetry-api" },
-    { name = "opentelemetry-exporter-otlp-proto-common" },
-    { name = "opentelemetry-proto" },
-    { name = "opentelemetry-sdk" },
-    { name = "requests" },
-    { name = "typing-extensions" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/77/32/826bfa1d80ecea24f47808de03cd4a0d13c17ecc07712f45123f0f61e4ac/opentelemetry_exporter_otlp_proto_http-1.42.1.tar.gz", hash = "sha256:bf142a21035d7571ac3a09cb2e5639f49886f243972883cfe777ed3bf02b734d", size = 25406, upload-time = "2026-05-21T16:32:56.807Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/d3/96/82cb223a1502f0787d4bbff12907f5f8d870a50731febcd5818d93ef9555/opentelemetry_exporter_otlp_proto_http-1.42.1-py3-none-any.whl", hash = "sha256:00a16da1b312a1d6c7233d600d557c91df71125af73020f3b9a7765bd699d59d", size = 21793, upload-time = "2026-05-21T16:32:35.277Z" },
-]
-
-[[package]]
-name = "opentelemetry-instrumentation"
-version = "0.63b1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "opentelemetry-api" },
-    { name = "opentelemetry-semantic-conventions" },
-    { name = "packaging" },
-    { name = "wrapt" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/da/6d/4de72d97ff54db1ed270c7a59c9b904b917c0ac7af429c086c388b824ddb/opentelemetry_instrumentation-0.63b1.tar.gz", hash = "sha256:32368d6ae52c8de20aa790a6ad86b10a76f09956092337ae37d675773990e541", size = 41081, upload-time = "2026-05-21T16:36:14.206Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/35/a1/9314e621c143e4d82a5bf7a43c2ff7a745d31023506336857607c8c543cc/opentelemetry_instrumentation-0.63b1-py3-none-any.whl", hash = "sha256:f1986716d52cc316ea5f60189098726a9071d8ecc0eee96c9ed110be08bade9c", size = 35577, upload-time = "2026-05-21T16:34:56.818Z" },
-]
-
 [[package]]
 name = "opentelemetry-proto"
 version = "1.42.1"