Feature/feat1017 (#2872)

### What problem does this PR solve?

1. fix: mid map show error in knowledge graph, juse because
```@antv/g6```version changed
2. feat: concurrent threads configuration support in graph extractor
3. fix: used tokens update failed for tenant
4. feat: timeout configuration support for llm
5. fix: regex error in graph extractor
6. feat: qwen rerank(```gte-rerank```) support
7. fix: timeout deal in knowledge graph index process. Now chat by
stream output, also, it is configuratable.
8. feat: ```qwen-long``` model configuration

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: chongchuanbing <chongchuanbing@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

rag/llm/rerank_model.py

@@ -390,3 +390,27 @@ class VoyageRerank(Base):
         for r in res.results:
             rank[r.index] = r.relevance_score
         return rank, res.total_tokens
+
+class QWenRerank(Base):
+    def __init__(self, key, model_name='gte-rerank', base_url=None, **kwargs):
+        import dashscope
+        self.api_key = key
+        self.model_name = dashscope.TextReRank.Models.gte_rerank if model_name is None else model_name
+
+    def similarity(self, query: str, texts: list):
+        import dashscope
+        from http import HTTPStatus
+        resp = dashscope.TextReRank.call(
+            api_key=self.api_key,
+            model=self.model_name,
+            query=query,
+            documents=texts,
+            top_n=len(texts),
+            return_documents=False
+        )
+        rank = np.zeros(len(texts), dtype=float)
+        if resp.status_code == HTTPStatus.OK:
+            for r in resp.output.results:
+                rank[r.index] = r.relevance_score
+            return rank, resp.usage.total_tokens
+        return rank, 0