perf: Optimize GraphRAG’s LOOP_PROMPT (#7356)

### What problem does this PR solve?

当前graphrag的LOOP_PROMPT，会导致模型输出Y之后，继续补充了实体和关系，比较浪费时间。参照[graph
rag](https://github.com/microsoft/graphrag/blob/main/graphrag/prompts/index/extract_graph.py)最新的代码，修改了LOOP_PROMPT，经过验证，修改后可以稳定的输出Y停止。

Currently, GraphRAG’s LOOP_PROMPT causes the model to keep appending
entities and relationships even after outputting “Y,” which wastes time.
Referring to the latest code in
[graphRAG](https://github.com/microsoft/graphrag/blob/main/graphrag/prompts/index/extract_graph.py),
I modified the LOOP_PROMPT, and after verification the updated prompt
reliably outputs “Y” and stops.

### Type of change

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

Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>

graphrag/general/graph_extractor.py

@@ -130,8 +130,9 @@ class GraphExtractor(Extractor):
             async with chat_limiter:
                 continuation = await trio.to_thread.run_sync(lambda: self._chat("", history, {"temperature": 0.8}))
             token_count += num_tokens_from_string("\n".join([m["content"] for m in history]) + response)
-            if continuation != "YES":
+            if continuation != "Y":
                 break
+            history.append({"role": "assistant", "content": "Y"})
 
         records = split_string_by_multi_markers(
             results,

graphrag/general/graph_prompt.py

@@ -106,7 +106,7 @@ Text: {input_text}
 Output:"""
 
 CONTINUE_PROMPT = "MANY entities were missed in the last extraction.  Add them below using the same format:\n"
-LOOP_PROMPT = "It appears some entities may have still been missed.  Answer YES | NO if there are still entities that need to be added.\n"
+LOOP_PROMPT = "It appears some entities may have still been missed. Answer Y if there are still entities that need to be added, or N if there are none. Please answer with a single letter Y or N.\n"
 
 SUMMARIZE_DESCRIPTIONS_PROMPT = """
 You are a helpful assistant responsible for generating a comprehensive summary of the data provided below.