feat(kag): catch unexpected exceptions (#298)

* x (#280)

* feat(bridge): spg server bridge (#283)

* x

* bridge add solver

* x

* feat(bridge): Spg server bridge check (#285)

* x

* bridge add solver

* x

* add invoke

* feat(common): llm client catch exception (#294)

* x

* bridge add solver

* x

* add invoke

* llm client catch error

* feat(solver): catch chunk retriever exception (#297)

* x

* bridge add solver

* x

* add invoke

* llm client catch error

* catch exception

* feat(common):llm except (#299)

* x

* bridge add solver

* x

* add invoke

* llm client catch error

* catch exception

* print llm invoke error info

* with except

* feat(common): force raise except (#300)

* x

* bridge add solver

* x

* add invoke

* llm client catch error

* catch exception

* print llm invoke error info

* with except

* force raise except

kag/builder/component/extractor/schema_constraint_extractor.py

@@ -90,7 +90,9 @@ class SchemaConstraintExtractor(ExtractorABC):
         Returns:
             The result of the named entity recognition operation.
         """
-        ner_result = self.llm.invoke({"input": passage}, self.ner_prompt)
+        ner_result = self.llm.invoke(
+            {"input": passage}, self.ner_prompt, with_except=False
+        )
         if self.external_graph:
             extra_ner_result = self.external_graph.ner(passage)
         else:
@@ -133,7 +135,9 @@ class SchemaConstraintExtractor(ExtractorABC):
             The result of the named entity standardization operation.
         """
         return self.llm.invoke(
-            {"input": passage, "named_entities": entities}, self.std_prompt
+            {"input": passage, "named_entities": entities},
+            self.std_prompt,
+            with_except=False,
         )
 
     @retry(stop=stop_after_attempt(3))
@@ -153,7 +157,9 @@ class SchemaConstraintExtractor(ExtractorABC):
 
             return []
         return self.llm.invoke(
-            {"input": passage, "entity_list": entities}, self.relation_prompt
+            {"input": passage, "entity_list": entities},
+            self.relation_prompt,
+            with_except=False,
         )
 
     @retry(stop=stop_after_attempt(3))
@@ -170,7 +176,7 @@ class SchemaConstraintExtractor(ExtractorABC):
         if self.event_prompt is None:
             logger.debug("Event extraction prompt not configured, skip.")
             return []
-        return self.llm.invoke({"input": passage}, self.event_prompt)
+        return self.llm.invoke({"input": passage}, self.event_prompt, with_except=False)
 
     def parse_nodes_and_edges(self, entities: List[Dict], category: str = None):
         """

kag/builder/component/extractor/schema_free_extractor.py

@@ -98,7 +98,9 @@ class SchemaFreeExtractor(ExtractorABC):
         Returns:
             The result of the named entity recognition operation.
         """
-        ner_result = self.llm.invoke({"input": passage}, self.ner_prompt)
+        ner_result = self.llm.invoke(
+            {"input": passage}, self.ner_prompt, with_except=False
+        )
         if self.external_graph:
             extra_ner_result = self.external_graph.ner(passage)
         else:
@@ -140,7 +142,9 @@ class SchemaFreeExtractor(ExtractorABC):
             Standardized entity information.
         """
         return self.llm.invoke(
-            {"input": passage, "named_entities": entities}, self.std_prompt
+            {"input": passage, "named_entities": entities},
+            self.std_prompt,
+            with_except=False,
         )
 
     @retry(stop=stop_after_attempt(3))
@@ -154,7 +158,9 @@ class SchemaFreeExtractor(ExtractorABC):
             The result of the triples extraction operation.
         """
         return self.llm.invoke(
-            {"input": passage, "entity_list": entities}, self.triple_prompt
+            {"input": passage, "entity_list": entities},
+            self.triple_prompt,
+            with_except=False,
         )
 
     def assemble_sub_graph_with_spg_records(self, entities: List[Dict]):

kag/interface/common/llm_client.py

@@ -77,7 +77,7 @@ class LLMClient(Registrable):
         variables: Dict[str, Any],
         prompt_op: PromptABC,
         with_json_parse: bool = True,
-        with_except: bool = False,
+        with_except: bool = True,
     ):
         """
         Call the model and process the result.
@@ -108,12 +108,12 @@ class LLMClient(Registrable):
             logger.debug(f"Result: {result}")
         except Exception as e:
             import traceback
-
-            logger.debug(f"Error {e} during invocation: {traceback.format_exc()}")
+            logger.info(f"Error {e} during invocation: {traceback.format_exc()}")
             if with_except:
                 raise RuntimeError(
                     f"LLM invoke exception, info: {e}\nllm input: \n{prompt}\nllm output: \n{response}"
                 )
+
         return result
 
     def batch(

kag/solver/retriever/impl/default_chunk_retrieval.py

@@ -171,7 +171,6 @@ class KAGRetriever(ChunkRetriever):
         Returns:
         dict: A dictionary with keys as document chunk IDs and values as the vector similarity scores.
         """
-        scores = dict()
         try:
             scores = query_sim_doc_cache.get(query)
             if scores:
@@ -186,6 +185,7 @@ class KAGRetriever(ChunkRetriever):
             scores = {item["node"]["id"]: item["score"] for item in top_k}
             query_sim_doc_cache.put(query, scores)
         except Exception as e:
+            scores = dict()
             logger.error(f"run calculate_sim_scores failed, info: {e}", exc_info=True)
         return scores
 
@@ -386,14 +386,20 @@ class KAGRetriever(ChunkRetriever):
         return matched_entities
 
     def _parse_ner_list(self, query):
-        ner_list = ner_cache.get(query)
-        if ner_list:
-            return ner_list
-        ner_list = self.named_entity_recognition(query)
-        if self.with_semantic:
-            std_ner_list = self.named_entity_standardization(query, ner_list)
-            self.append_official_name(ner_list, std_ner_list)
-        ner_cache.put(query, ner_list)
+        ner_list = []
+        try:
+            ner_list = ner_cache.get(query)
+            if ner_list:
+                return ner_list
+            ner_list = self.named_entity_recognition(query)
+            if self.with_semantic:
+                std_ner_list = self.named_entity_standardization(query, ner_list)
+                self.append_official_name(ner_list, std_ner_list)
+            ner_cache.put(query, ner_list)
+        except Exception as e:
+            if not ner_list:
+                ner_list = []
+            logger.warning(f"_parse_ner_list {query} failed {e}", exc_info=True)
         return ner_list
 
     def recall_docs(
@@ -504,15 +510,20 @@ class KAGRetriever(ChunkRetriever):
             else:
                 doc_score = doc_ids[doc_id]
             counter += 1
-            node = self.graph_api.get_entity_prop_by_id(
-                label=self.schema.get_label_within_prefix(CHUNK_TYPE),
-                biz_id=doc_id,
-            )
-            node_dict = dict(node.items())
-            matched_docs.append(
-                f"#{node_dict['name']}#{node_dict['content']}#{doc_score}"
-            )
-            hits_docs.add(node_dict["name"])
+            try:
+                node = self.graph_api.get_entity_prop_by_id(
+                    label=self.schema.get_label_within_prefix(CHUNK_TYPE),
+                    biz_id=doc_id,
+                )
+                node_dict = dict(node.items())
+                matched_docs.append(
+                    f"#{node_dict['name']}#{node_dict['content']}#{doc_score}"
+                )
+                hits_docs.add(node_dict["name"])
+            except Exception as e:
+                logger.warning(
+                    f"{doc_id} get_entity_prop_by_id failed: {e}", exc_info=True
+                )
         query = "\n".join(queries)
         try:
             text_matched = self.search_api.search_text(