Use consistent log file names, introduced initLogger (#3403)

### What problem does this PR solve?

Use consistent log file names, introduced initLogger

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

graphrag/claim_extractor.py

@@ -5,6 +5,7 @@ Reference:
  - [graphrag](https://github.com/microsoft/graphrag)
 """
 
+import logging
 import argparse
 import json
 import re
@@ -17,7 +18,6 @@ import tiktoken
 from graphrag.claim_prompt import CLAIM_EXTRACTION_PROMPT, CONTINUE_PROMPT, LOOP_PROMPT
 from rag.llm.chat_model import Base as CompletionLLM
 from graphrag.utils import ErrorHandlerFn, perform_variable_replacements
-from api.utils.log_utils import logger
 
 DEFAULT_TUPLE_DELIMITER = "<|>"
 DEFAULT_RECORD_DELIMITER = "##"
@@ -126,7 +126,7 @@ class ClaimExtractor:
                 ]
                 source_doc_map[document_id] = text
             except Exception as e:
-                logger.exception("error extracting claim")
+                logging.exception("error extracting claim")
                 self._on_error(
                     e,
                     traceback.format_exc(),
@@ -265,4 +265,4 @@ if __name__ == "__main__":
         "claim_description": ""
     }
     claim = ex(info)
-    logger.info(json.dumps(claim.output, ensure_ascii=False, indent=2))
+    logging.info(json.dumps(claim.output, ensure_ascii=False, indent=2))

graphrag/community_reports_extractor.py

@@ -5,6 +5,7 @@ Reference:
  - [graphrag](https://github.com/microsoft/graphrag)
 """
 
+import logging
 import json
 import re
 import traceback
@@ -19,7 +20,6 @@ from rag.llm.chat_model import Base as CompletionLLM
 from graphrag.utils import ErrorHandlerFn, perform_variable_replacements, dict_has_keys_with_types
 from rag.utils import num_tokens_from_string
 from timeit import default_timer as timer
-from api.utils.log_utils import logger
 
 
 @dataclass
@@ -80,7 +80,7 @@ class CommunityReportsExtractor:
                     response = re.sub(r"[^\}]*$", "", response)
                     response = re.sub(r"\{\{", "{", response)
                     response = re.sub(r"\}\}", "}", response)
-                    logger.info(response)
+                    logging.debug(response)
                     response = json.loads(response)
                     if not dict_has_keys_with_types(response, [
                                 ("title", str),
@@ -92,7 +92,7 @@ class CommunityReportsExtractor:
                     response["weight"] = weight
                     response["entities"] = ents
                 except Exception as e:
-                    logger.exception("CommunityReportsExtractor got exception")
+                    logging.exception("CommunityReportsExtractor got exception")
                     self._on_error(e, traceback.format_exc(), None)
                     continue
 

graphrag/description_summary.py

@@ -5,19 +5,11 @@ Reference:
  - [graphrag](https://github.com/microsoft/graphrag)
 """
 
-import argparse
-import html
 import json
-import logging
-import numbers
-import re
-import traceback
-from collections.abc import Callable
 from dataclasses import dataclass
 
 from graphrag.utils import ErrorHandlerFn, perform_variable_replacements
 from rag.llm.chat_model import Base as CompletionLLM
-import networkx as nx
 
 from rag.utils import num_tokens_from_string
 

graphrag/entity_resolution.py

@@ -13,8 +13,8 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-import itertools
 import logging
+import itertools
 import re
 import traceback
 from dataclasses import dataclass

graphrag/index.py

@@ -13,6 +13,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+import logging
 import os
 from concurrent.futures import ThreadPoolExecutor
 import json
@@ -28,7 +29,6 @@ from graphrag.graph_extractor import GraphExtractor, DEFAULT_ENTITY_TYPES
 from graphrag.mind_map_extractor import MindMapExtractor
 from rag.nlp import rag_tokenizer
 from rag.utils import num_tokens_from_string
-from api.utils.log_utils import logger
 
 
 def graph_merge(g1, g2):
@@ -95,7 +95,7 @@ def build_knowledge_graph_chunks(tenant_id: str, chunks: List[str], callback, en
     chunks = []
     for n, attr in graph.nodes(data=True):
         if attr.get("rank", 0) == 0:
-            logger.info(f"Ignore entity: {n}")
+            logging.debug(f"Ignore entity: {n}")
             continue
         chunk = {
             "name_kwd": n,
@@ -137,7 +137,7 @@ def build_knowledge_graph_chunks(tenant_id: str, chunks: List[str], callback, en
     mg = mindmap(_chunks).output
     if not len(mg.keys()): return chunks
 
-    logger.info(json.dumps(mg, ensure_ascii=False, indent=2))
+    logging.debug(json.dumps(mg, ensure_ascii=False, indent=2))
     chunks.append(
         {
             "content_with_weight": json.dumps(mg, ensure_ascii=False, indent=2),

graphrag/leiden.py

@@ -14,8 +14,6 @@ from graspologic.utils import largest_connected_component
 import networkx as nx
 from networkx import is_empty
 
-log = logging.getLogger(__name__)
-
 
 def _stabilize_graph(graph: nx.Graph) -> nx.Graph:
     """Ensure an undirected graph with the same relationships will always be read the same way."""
@@ -99,7 +97,7 @@ def run(graph: nx.Graph, args: dict[str, Any]) -> dict[int, dict[str, dict]]:
     max_cluster_size = args.get("max_cluster_size", 12)
     use_lcc = args.get("use_lcc", True)
     if args.get("verbose", False):
-        log.info(
+        logging.debug(
             "Running leiden with max_cluster_size=%s, lcc=%s", max_cluster_size, use_lcc
         )
     if not graph.nodes(): return {}

graphrag/mind_map_extractor.py

@@ -14,8 +14,8 @@
 #  limitations under the License.
 #
 
-import collections
 import logging
+import collections
 import os
 import re
 import traceback
@@ -29,7 +29,6 @@ from rag.llm.chat_model import Base as CompletionLLM
 import markdown_to_json
 from functools import reduce
 from rag.utils import num_tokens_from_string
-from api.utils.log_utils import logger
 
 
 @dataclass
@@ -193,6 +192,6 @@ class MindMapExtractor:
         gen_conf = {"temperature": 0.5}
         response = self._llm.chat(text, [{"role": "user", "content": "Output:"}], gen_conf)
         response = re.sub(r"```[^\n]*", "", response)
-        logger.info(response)
-        logger.info(self._todict(markdown_to_json.dictify(response)))
+        logging.debug(response)
+        logging.debug(self._todict(markdown_to_json.dictify(response)))
         return self._todict(markdown_to_json.dictify(response))