Merge branch 'microsoft:main' into master

.semversioner/next-release/patch-20240808225534741702.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Fix file dumps using json for non ASCII chars"
+}

graphrag/index/cache/json_pipeline_cache.py

@@ -44,7 +44,9 @@ async def set(self, key: str, value: Any, debug_data: dict | None = None) -> Non
         if value is None:
             return
         data = {"result": value, **(debug_data or {})}
-        await self._storage.set(key, json.dumps(data), encoding=self._encoding)
+        await self._storage.set(
+            key, json.dumps(data, ensure_ascii=False), encoding=self._encoding
+        )
 
     async def has(self, key: str) -> bool:
         """Has method definition."""

graphrag/index/graph/extractors/summarize/description_summary_extractor.py

@@ -127,7 +127,9 @@ async def _summarize_descriptions_with_llm(
             name="summarize",
             variables={
                 self._entity_name_key: json.dumps(items),
-                self._input_descriptions_key: json.dumps(sorted(descriptions)),
+                self._input_descriptions_key: json.dumps(
+                    sorted(descriptions), ensure_ascii=False
+                ),
             },
             model_parameters={"max_tokens": self._max_summary_length},
         )

graphrag/index/reporting/blob_workflow_callbacks.py

@@ -78,7 +78,7 @@ def _write_log(self, log: dict[str, Any]):
         blob_client = self._blob_service_client.get_blob_client(
             self._container_name, self._blob_name
         )
-        blob_client.append_block(json.dumps(log) + "\n")
+        blob_client.append_block(json.dumps(log, ensure_ascii=False) + "\n")
 
         # update the blob's block count
         self._num_blocks += 1

graphrag/index/reporting/file_workflow_callbacks.py

@@ -34,13 +34,16 @@ def on_error(
     ):
         """Handle when an error occurs."""
         self._out_stream.write(
-            json.dumps({
-                "type": "error",
-                "data": message,
-                "stack": stack,
-                "source": str(cause),
-                "details": details,
-            })
+            json.dumps(
+                {
+                    "type": "error",
+                    "data": message,
+                    "stack": stack,
+                    "source": str(cause),
+                    "details": details,
+                },
+                ensure_ascii=False,
+            )
             + "\n"
         )
         message = f"{message} details={details}"
@@ -49,14 +52,21 @@ def on_error(
     def on_warning(self, message: str, details: dict | None = None):
         """Handle when a warning occurs."""
         self._out_stream.write(
-            json.dumps({"type": "warning", "data": message, "details": details}) + "\n"
+            json.dumps(
+                {"type": "warning", "data": message, "details": details},
+                ensure_ascii=False,
+            )
+            + "\n"
         )
         _print_warning(message)
 
     def on_log(self, message: str, details: dict | None = None):
         """Handle when a log message is produced."""
         self._out_stream.write(
-            json.dumps({"type": "log", "data": message, "details": details}) + "\n"
+            json.dumps(
+                {"type": "log", "data": message, "details": details}, ensure_ascii=False
+            )
+            + "\n"
         )
 
         message = f"{message} details={details}"

graphrag/index/run.py

@@ -234,7 +234,9 @@ async def run_pipeline(
         )
 
     async def dump_stats() -> None:
-        await storage.set("stats.json", json.dumps(asdict(stats), indent=4))
+        await storage.set(
+            "stats.json", json.dumps(asdict(stats), indent=4, ensure_ascii=False)
+        )
 
     async def load_table_from_storage(name: str) -> pd.DataFrame:
         if not await storage.has(name):

graphrag/index/text_splitting/text_splitting.py

@@ -224,7 +224,7 @@ def _append_to_result(self, chunk_list: list[str], new_chunk: list[str]):
         """Append the current chunk to the result."""
         if new_chunk and len(new_chunk) > 0:
             if self._type == TextListSplitterType.JSON:
-                chunk_list.append(json.dumps(new_chunk))
+                chunk_list.append(json.dumps(new_chunk, ensure_ascii=False))
             else:
                 chunk_list.append(self._output_delimiter.join(new_chunk))
 

graphrag/index/verbs/graph/report/strategies/graph_intelligence/run_graph_intelligence.py

@@ -82,7 +82,7 @@ async def _run_extractor(
             rank_explanation=report.get("rating_explanation", ""),
             summary=report.get("summary", ""),
             findings=report.get("findings", []),
-            full_content_json=json.dumps(report, indent=4),
+            full_content_json=json.dumps(report, indent=4, ensure_ascii=False),
         )
     except Exception as e:
         log.exception("Error processing community: %s", community)

graphrag/index/verbs/snapshot_rows.py

@@ -49,9 +49,11 @@ def get_row_name(row: Any, row_idx: Any):
             if fmt.format == "json":
                 await storage.set(
                     f"{row_name}.{extension}",
-                    json.dumps(row[column])
-                    if column is not None
-                    else json.dumps(row.to_dict()),
+                    (
+                        json.dumps(row[column], ensure_ascii=False)
+                        if column is not None
+                        else json.dumps(row.to_dict(), ensure_ascii=False)
+                    ),
                 )
             elif fmt.format == "text":
                 if column is None:
@@ -65,9 +67,11 @@ def get_row_name(row: Any, row_idx: Any):
 def _parse_formats(formats: list[str | dict[str, Any]]) -> list[FormatSpecifier]:
     """Parse the formats into a list of FormatSpecifiers."""
     return [
-        FormatSpecifier(**fmt)
-        if isinstance(fmt, dict)
-        else FormatSpecifier(format=fmt, extension=_get_format_extension(fmt))
+        (
+            FormatSpecifier(**fmt)
+            if isinstance(fmt, dict)
+            else FormatSpecifier(format=fmt, extension=_get_format_extension(fmt))
+        )
         for fmt in formats
     ]