Merge branch 'main' of https://github.com/open-sciencelab/GraphGen into feature/protein-qa

Author: CHERRY-ui8

.env.example

@@ -14,6 +14,14 @@ TRAINEE_MODEL=gpt-4o-mini
 TRAINEE_BASE_URL=
 TRAINEE_API_KEY=
 
+# azure_openai_api
+# SYNTHESIZER_BACKEND=azure_openai_api
+# The following is the same as your "Deployment name" in Azure
+# SYNTHESIZER_MODEL=<your-deployment-name>
+# SYNTHESIZER_BASE_URL=https://<your-resource-name>.openai.azure.com/openai/deployments/<your-deployment-name>/chat/completions
+# SYNTHESIZER_API_KEY=
+# SYNTHESIZER_API_VERSION=<api-version>
+
 # # ollama_api
 # SYNTHESIZER_BACKEND=ollama_api
 # SYNTHESIZER_MODEL=gemma3

.pylintrc

@@ -100,7 +100,7 @@ source-roots=
 
 # When enabled, pylint would attempt to guess common misconfiguration and emit
 # user-friendly hints instead of false-positive error messages.
-suggestion-mode=yes
+# suggestion-mode=yes
 
 # Allow loading of arbitrary C extensions. Extensions are imported into the
 # active Python interpreter and may run arbitrary code.

README.md

@@ -16,7 +16,6 @@
 
 [![Hugging Face](https://img.shields.io/badge/Demo-on%20HF-blue?logo=huggingface&logoColor=yellow)](https://huggingface.co/spaces/chenzihong/GraphGen)
 [![Model Scope](https://img.shields.io/badge/%F0%9F%A4%96%20Demo-on%20MS-green)](https://modelscope.cn/studios/chenzihong/GraphGen)
-[![OpenXLab](https://img.shields.io/badge/Demo-on%20OpenXLab-blue?logo=openxlab&logoColor=yellow)](https://g-app-center-120612-6433-jpdvmvp.openxlab.space)
 
 
 GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
@@ -107,7 +106,7 @@ Users can flexibly configure according to the needs of synthetic data.
 
 ## 🚀 Quick Start
 
-Experience GraphGen through [Web](https://g-app-center-120612-6433-jpdvmvp.openxlab.space) or [Backup Web Entrance](https://openxlab.org.cn/apps/detail/chenzihonga/GraphGen)
+Experience GraphGen Demo through [Huggingface](https://huggingface.co/spaces/chenzihong/GraphGen) or [Modelscope](https://modelscope.cn/studios/chenzihong/GraphGen).
 
 For any questions, please check [FAQ](https://github.com/open-sciencelab/GraphGen/issues/10), open new [issue](https://github.com/open-sciencelab/GraphGen/issues) or join our [wechat group](https://cdn.vansin.top/internlm/dou.jpg) and ask.
 

README_zh.md

@@ -16,7 +16,6 @@
 
 [![Hugging Face](https://img.shields.io/badge/Demo-on%20HF-blue?logo=huggingface&logoColor=yellow)](https://huggingface.co/spaces/chenzihong/GraphGen)
 [![Model Scope](https://img.shields.io/badge/%F0%9F%A4%96%20Demo-on%20MS-green)](https://modelscope.cn/studios/chenzihong/GraphGen)
-[![OpenXLab](https://img.shields.io/badge/Demo-on%20OpenXLab-blue?logo=openxlab&logoColor=yellow)](https://g-app-center-120612-6433-jpdvmvp.openxlab.space)
 
 GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
 
@@ -105,7 +104,7 @@ GraphGen 首先根据源文本构建细粒度的知识图谱，然后利用期
 
 ## 🚀 快速开始
 
-通过 [Web](https://g-app-center-120612-6433-jpdvmvp.openxlab.space) 或 [备用 Web 入口](https://openxlab.org.cn/apps/detail/chenzihonga/GraphGen) 体验 GraphGen。
+通过 [Huggingface](https://huggingface.co/spaces/chenzihong/GraphGen) 或 [Modelscope](https://modelscope.cn/studios/chenzihong/GraphGen) 体验 GraphGen。
 
 如有任何问题，请查看 [FAQ](https://github.com/open-sciencelab/GraphGen/issues/10)、提交新的 [issue](https://github.com/open-sciencelab/GraphGen/issues) 或加入我们的[微信群](https://cdn.vansin.top/internlm/dou.jpg)咨询。
 

baselines/Genie/genie.py

@@ -122,7 +122,7 @@ async def process_chunk(content: str):
     load_dotenv()
 
     llm_client = OpenAIClient(
-        model_name=os.getenv("SYNTHESIZER_MODEL"),
+        model=os.getenv("SYNTHESIZER_MODEL"),
         api_key=os.getenv("SYNTHESIZER_API_KEY"),
         base_url=os.getenv("SYNTHESIZER_BASE_URL"),
     )

baselines/LongForm/longform.py

@@ -89,7 +89,7 @@ async def process_chunk(content: str):
     load_dotenv()
 
     llm_client = OpenAIClient(
-        model_name=os.getenv("SYNTHESIZER_MODEL"),
+        model=os.getenv("SYNTHESIZER_MODEL"),
         api_key=os.getenv("SYNTHESIZER_API_KEY"),
         base_url=os.getenv("SYNTHESIZER_BASE_URL"),
     )

baselines/SELF-QA/self-qa.py

@@ -156,7 +156,7 @@ async def process_chunk(content: str):
     load_dotenv()
 
     llm_client = OpenAIClient(
-        model_name=os.getenv("SYNTHESIZER_MODEL"),
+        model=os.getenv("SYNTHESIZER_MODEL"),
         api_key=os.getenv("SYNTHESIZER_API_KEY"),
         base_url=os.getenv("SYNTHESIZER_BASE_URL"),
     )

baselines/Wrap/wrap.py

@@ -109,7 +109,7 @@ async def process_chunk(content: str):
     load_dotenv()
 
     llm_client = OpenAIClient(
-        model_name=os.getenv("SYNTHESIZER_MODEL"),
+        model=os.getenv("SYNTHESIZER_MODEL"),
         api_key=os.getenv("SYNTHESIZER_API_KEY"),
         base_url=os.getenv("SYNTHESIZER_BASE_URL"),
     )

graphgen/bases/base_partitioner.py

@@ -39,16 +39,16 @@ async def community2batch(
             edges = comm.edges
             nodes_data = []
             for node in nodes:
-                node_data = await g.get_node(node)
+                node_data = g.get_node(node)
                 if node_data:
                     nodes_data.append((node, node_data))
             edges_data = []
             for u, v in edges:
-                edge_data = await g.get_edge(u, v)
+                edge_data = g.get_edge(u, v)
                 if edge_data:
                     edges_data.append((u, v, edge_data))
                 else:
-                    edge_data = await g.get_edge(v, u)
+                    edge_data = g.get_edge(v, u)
                     if edge_data:
                         edges_data.append((v, u, edge_data))
             batches.append((nodes_data, edges_data))

graphgen/bases/base_storage.py

@@ -9,103 +9,99 @@ class StorageNameSpace:
     working_dir: str = None
     namespace: str = None
 
-    async def index_done_callback(self):
+    def index_done_callback(self):
         """commit the storage operations after indexing"""
 
-    async def query_done_callback(self):
+    def query_done_callback(self):
         """commit the storage operations after querying"""
 
 
 class BaseListStorage(Generic[T], StorageNameSpace):
-    async def all_items(self) -> list[T]:
+    def all_items(self) -> list[T]:
         raise NotImplementedError
 
-    async def get_by_index(self, index: int) -> Union[T, None]:
+    def get_by_index(self, index: int) -> Union[T, None]:
         raise NotImplementedError
 
-    async def append(self, data: T):
+    def append(self, data: T):
         raise NotImplementedError
 
-    async def upsert(self, data: list[T]):
+    def upsert(self, data: list[T]):
         raise NotImplementedError
 
-    async def drop(self):
+    def drop(self):
         raise NotImplementedError
 
 
 class BaseKVStorage(Generic[T], StorageNameSpace):
-    async def all_keys(self) -> list[str]:
+    def all_keys(self) -> list[str]:
         raise NotImplementedError
 
-    async def get_by_id(self, id: str) -> Union[T, None]:
+    def get_by_id(self, id: str) -> Union[T, None]:
         raise NotImplementedError
 
-    async def get_by_ids(
+    def get_by_ids(
         self, ids: list[str], fields: Union[set[str], None] = None
     ) -> list[Union[T, None]]:
         raise NotImplementedError
 
-    async def get_all(self) -> dict[str, T]:
+    def get_all(self) -> dict[str, T]:
         raise NotImplementedError
 
-    async def filter_keys(self, data: list[str]) -> set[str]:
+    def filter_keys(self, data: list[str]) -> set[str]:
         """return un-exist keys"""
         raise NotImplementedError
 
-    async def upsert(self, data: dict[str, T]):
+    def upsert(self, data: dict[str, T]):
         raise NotImplementedError
 
-    async def drop(self):
+    def drop(self):
         raise NotImplementedError
 
 
 class BaseGraphStorage(StorageNameSpace):
-    async def has_node(self, node_id: str) -> bool:
+    def has_node(self, node_id: str) -> bool:
         raise NotImplementedError
 
-    async def has_edge(self, source_node_id: str, target_node_id: str) -> bool:
+    def has_edge(self, source_node_id: str, target_node_id: str) -> bool:
         raise NotImplementedError
 
-    async def node_degree(self, node_id: str) -> int:
+    def node_degree(self, node_id: str) -> int:
         raise NotImplementedError
 
-    async def edge_degree(self, src_id: str, tgt_id: str) -> int:
+    def edge_degree(self, src_id: str, tgt_id: str) -> int:
         raise NotImplementedError
 
-    async def get_node(self, node_id: str) -> Union[dict, None]:
+    def get_node(self, node_id: str) -> Union[dict, None]:
         raise NotImplementedError
 
-    async def update_node(self, node_id: str, node_data: dict[str, str]):
+    def update_node(self, node_id: str, node_data: dict[str, str]):
         raise NotImplementedError
 
-    async def get_all_nodes(self) -> Union[list[tuple[str, dict]], None]:
+    def get_all_nodes(self) -> Union[list[tuple[str, dict]], None]:
         raise NotImplementedError
 
-    async def get_edge(
-        self, source_node_id: str, target_node_id: str
-    ) -> Union[dict, None]:
+    def get_edge(self, source_node_id: str, target_node_id: str) -> Union[dict, None]:
         raise NotImplementedError
 
-    async def update_edge(
+    def update_edge(
         self, source_node_id: str, target_node_id: str, edge_data: dict[str, str]
     ):
         raise NotImplementedError
 
-    async def get_all_edges(self) -> Union[list[tuple[str, str, dict]], None]:
+    def get_all_edges(self) -> Union[list[tuple[str, str, dict]], None]:
         raise NotImplementedError
 
-    async def get_node_edges(
-        self, source_node_id: str
-    ) -> Union[list[tuple[str, str]], None]:
+    def get_node_edges(self, source_node_id: str) -> Union[list[tuple[str, str]], None]:
         raise NotImplementedError
 
-    async def upsert_node(self, node_id: str, node_data: dict[str, str]):
+    def upsert_node(self, node_id: str, node_data: dict[str, str]):
         raise NotImplementedError
 
-    async def upsert_edge(
+    def upsert_edge(
         self, source_node_id: str, target_node_id: str, edge_data: dict[str, str]
     ):
         raise NotImplementedError
 
-    async def delete_node(self, node_id: str):
+    def delete_node(self, node_id: str):
         raise NotImplementedError