Merge pull request #1 from Dormiveglia-elf/dev-zhenyu

Doc Refinement and Fixes

config.yaml

@@ -0,0 +1,34 @@
+# OpenAI Configuration
+openai:
+  embedding_model: "text-embedding-ada-002"
+  model: "gpt-4o"
+  api_key: "***"
+  base_url: "***"
+
+# GLM Configuration
+glm:
+  model: "glm-4-plus"
+  api_key: "***"
+  base_url: "https://open.bigmodel.cn/api/paas/v4"
+  embedding_model: "embedding-3"
+
+# Deepseek Configuration
+deepseek:
+  model: "deepseek-chat"
+  api_key: "***"
+  base_url: "https://api.deepseek.com"
+
+# Model Parameters
+model_params:
+  openai_embedding_dim: 1536
+  glm_embedding_dim: 2048
+  max_token_size: 8192
+
+# HiRAG Configuration
+hirag:
+  working_dir: "your_work_dir"
+  enable_llm_cache: false
+  enable_hierachical_mode: true
+  embedding_batch_num: 6
+  embedding_func_max_async: 8
+  enable_naive_rag: true

readme.md

@@ -34,7 +34,7 @@ print("Perform hi search:")
 print(graph_func.query("The question you want to ask?", param=QueryParam(mode="hi")))
 ```
 
-Or if you want to employ HiRAG with DeepSeek, ChatGLM, or other third-party retrieval api, here are the examples in `./hi_Search_deepseek.py`, `./hi_search_glm.py`, and `./hi_search_openai.py`. The API keys and the LLM configurations can be set at `config.yaml`.
+Or if you want to employ HiRAG with DeepSeek, ChatGLM, or other third-party retrieval api, here are the examples in `./hi_Search_deepseek.py`, `./hi_Search_glm.py`, and `./hi_Search_openai.py`. The API keys and the LLM configurations can be set at `./config.yaml`.
 
 
 ## Evaluation
@@ -243,6 +243,12 @@ python batch_eval.py -m result -api openai
 |           |Diversity|           3.5|             **96.5**|
 |           |Overall|           0.0|             **100.0**|
 
+## Acknowledgement
+We gratefully acknowledge the use of the following open-source projects in our work:
+- [nano-graphrag](https://github.com/gusye1234/nano-graphrag): a simple, easy-to-hack GraphRAG implementation
+
+- [RAPTOR](https://github.com/parthsarthi03/raptor): a novel approach to retrieval-augmented language models by constructing a recursive tree structure from documents.
+
 ## Cite Us
 ```
 @misc{huang2025retrievalaugmentedgenerationhierarchicalknowledge,