Refa: GraphRAG and explaining GraphRAG stalling behavior on large files (#8223)

### What problem does this PR solve?

This PR investigates the cause of #7957.

TL;DR: Incorrect similarity calculations lead to too many candidates.
Since candidate selection involves interaction with the LLM, this causes
significant delays in the program.

What this PR does:

1. **Fix similarity calculation**:
When processing a 64 pages government document, the corrected similarity
calculation reduces the number of candidates from over 100,000 to around
16,000. With a default batch size of 100 pairs per LLM call, this fix
reduces unnecessary LLM interactions from over 1,000 calls to around
160, a roughly 10x improvement.
2. **Add concurrency and timeout limits**: 
Up to 5 entity types are processed in "parallel", each with a 180-second
timeout. These limits may be configurable in future updates.
3. **Improve logging**:
The candidate resolution process now reports progress in real time.
4. **Mitigates potential concurrency risks**


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring

graphrag/general/community_reports_extractor.py

@@ -89,7 +89,15 @@ class CommunityReportsExtractor(Extractor):
             text = perform_variable_replacements(self._extraction_prompt, variables=prompt_variables)
             gen_conf = {"temperature": 0.3}
             async with chat_limiter:
-                response = await trio.to_thread.run_sync(lambda: self._chat(text, [{"role": "user", "content": "Output:"}], gen_conf))
+                try:
+                    with trio.move_on_after(120) as cancel_scope:
+                        response = await trio.to_thread.run_sync( self._chat, text, [{"role": "user", "content": "Output:"}], gen_conf)
+                    if cancel_scope.cancelled_caught:
+                        logging.warning("extract_community_report._chat timeout, skipping...")
+                        return
+                except Exception as e:
+                    logging.error(f"extract_community_report._chat failed: {e}")
+                    return
             token_count += num_tokens_from_string(text + response)
             response = re.sub(r"^[^\{]*", "", response)
             response = re.sub(r"[^\}]*$", "", response)