Feat: add citation option to agent and enlarge the timeouts. (#9484)

### What problem does this PR solve?

#9422

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

graphrag/entity_resolution.py

@@ -106,7 +106,7 @@ class EntityResolution(Extractor):
             nonlocal remain_candidates_to_resolve, callback
             async with semaphore:
                 try:
-                    with trio.move_on_after(180) as cancel_scope:
+                    with trio.move_on_after(280) as cancel_scope:
                         await self._resolve_candidate(candidate_batch, result_set, result_lock)
                         remain_candidates_to_resolve = remain_candidates_to_resolve - len(candidate_batch[1])
                         callback(msg=f"Resolved {len(candidate_batch[1])} pairs, {remain_candidates_to_resolve} are remained to resolve. ")
@@ -169,7 +169,7 @@ class EntityResolution(Extractor):
         logging.info(f"Created resolution prompt {len(text)} bytes for {len(candidate_resolution_i[1])} entity pairs of type {candidate_resolution_i[0]}")
         async with chat_limiter:
             try:
-                with trio.move_on_after(120) as cancel_scope:
+                with trio.move_on_after(240) as cancel_scope:
                     response = await trio.to_thread.run_sync(self._chat, text, [{"role": "user", "content": "Output:"}], {})
                 if cancel_scope.cancelled_caught:
                     logging.warning("_resolve_candidate._chat timeout, skipping...")

graphrag/general/community_reports_extractor.py

@@ -92,7 +92,7 @@ class CommunityReportsExtractor(Extractor):
             text = perform_variable_replacements(self._extraction_prompt, variables=prompt_variables)
             async with chat_limiter:
                 try:
-                    with trio.move_on_after(80) as cancel_scope:
+                    with trio.move_on_after(180) as cancel_scope:
                         response = await trio.to_thread.run_sync( self._chat, text, [{"role": "user", "content": "Output:"}], {})
                     if cancel_scope.cancelled_caught:
                         logging.warning("extract_community_report._chat timeout, skipping...")

graphrag/general/index.py

@@ -57,20 +57,22 @@ async def run_graphrag(
     ):
         chunks.append(d["content_with_weight"])
 
-    subgraph = await generate_subgraph(
-        LightKGExt
-        if "method" not in row["kb_parser_config"].get("graphrag", {}) or row["kb_parser_config"]["graphrag"]["method"] != "general"
-        else GeneralKGExt,
-        tenant_id,
-        kb_id,
-        doc_id,
-        chunks,
-        language,
-        row["kb_parser_config"]["graphrag"].get("entity_types", []),
-        chat_model,
-        embedding_model,
-        callback,
-    )
+    with trio.fail_after(len(chunks)*60):
+        subgraph = await generate_subgraph(
+            LightKGExt
+            if "method" not in row["kb_parser_config"].get("graphrag", {}) or row["kb_parser_config"]["graphrag"]["method"] != "general"
+            else GeneralKGExt,
+            tenant_id,
+            kb_id,
+            doc_id,
+            chunks,
+            language,
+            row["kb_parser_config"]["graphrag"].get("entity_types", []),
+            chat_model,
+            embedding_model,
+            callback,
+        )
+
     if not subgraph:
         return
 
@@ -125,7 +127,6 @@ async def run_graphrag(
     return
 
 
-@timeout(60*60, 1)
 async def generate_subgraph(
     extractor: Extractor,
     tenant_id: str,