remove None union types when default values are set

Author: dworthen

graphrag/config/models/basic_search_config.py

@@ -22,15 +22,15 @@ class BasicSearchConfig(BaseModel):
         description="The conversation history maximum turns.",
         default=defs.BASIC_SEARCH_CONVERSATION_HISTORY_MAX_TURNS,
     )
-    temperature: float | None = Field(
+    temperature: float = Field(
         description="The temperature to use for token generation.",
         default=defs.BASIC_SEARCH_LLM_TEMPERATURE,
     )
-    top_p: float | None = Field(
+    top_p: float = Field(
         description="The top-p value to use for token generation.",
         default=defs.BASIC_SEARCH_LLM_TOP_P,
     )
-    n: int | None = Field(
+    n: int = Field(
         description="The number of completions to generate.",
         default=defs.BASIC_SEARCH_LLM_N,
     )

graphrag/config/models/cluster_graph_config.py

@@ -18,7 +18,7 @@ class ClusterGraphConfig(BaseModel):
         description="Whether to use the largest connected component.",
         default=defs.USE_LCC,
     )
-    seed: int | None = Field(
+    seed: int = Field(
         description="The seed to use for the clustering.",
         default=defs.CLUSTER_GRAPH_SEED,
     )

graphrag/config/models/global_search_config.py

@@ -20,15 +20,15 @@ class GlobalSearchConfig(BaseModel):
     knowledge_prompt: str | None = Field(
         description="The global search general prompt to use.", default=None
     )
-    temperature: float | None = Field(
+    temperature: float = Field(
         description="The temperature to use for token generation.",
         default=defs.GLOBAL_SEARCH_LLM_TEMPERATURE,
     )
-    top_p: float | None = Field(
+    top_p: float = Field(
         description="The top-p value to use for token generation.",
         default=defs.GLOBAL_SEARCH_LLM_TOP_P,
     )
-    n: int | None = Field(
+    n: int = Field(
         description="The number of completions to generate.",
         default=defs.GLOBAL_SEARCH_LLM_N,
     )

graphrag/config/models/input_config.py

@@ -30,7 +30,7 @@ class InputConfig(BaseModel):
     container_name: str | None = Field(
         description="The azure blob storage container name to use.", default=None
     )
-    encoding: str | None = Field(
+    encoding: str = Field(
         description="The input file encoding to use.",
         default=defs.INPUT_FILE_ENCODING,
     )

graphrag/config/models/language_model_config.py

@@ -76,27 +76,27 @@ def _validate_encoding_model(self) -> None:
         if self.encoding_model.strip() == "":
             self.encoding_model = tiktoken.encoding_name_for_model(self.model)
 
-    max_tokens: int | None = Field(
+    max_tokens: int = Field(
         description="The maximum number of tokens to generate.",
         default=defs.LLM_MAX_TOKENS,
     )
-    temperature: float | None = Field(
+    temperature: float = Field(
         description="The temperature to use for token generation.",
         default=defs.LLM_TEMPERATURE,
     )
-    top_p: float | None = Field(
+    top_p: float = Field(
         description="The top-p value to use for token generation.",
         default=defs.LLM_TOP_P,
     )
-    n: int | None = Field(
+    n: int = Field(
         description="The number of completions to generate.",
         default=defs.LLM_N,
     )
-    frequency_penalty: float | None = Field(
+    frequency_penalty: float = Field(
         description="The frequency penalty to use for token generation.",
         default=defs.LLM_FREQUENCY_PENALTY,
     )
-    presence_penalty: float | None = Field(
+    presence_penalty: float = Field(
         description="The presence penalty to use for token generation.",
         default=defs.LLM_PRESENCE_PENALTY,
     )

graphrag/config/models/local_search_config.py

@@ -34,15 +34,15 @@ class LocalSearchConfig(BaseModel):
         description="The top k mapped relations.",
         default=defs.LOCAL_SEARCH_TOP_K_RELATIONSHIPS,
     )
-    temperature: float | None = Field(
+    temperature: float = Field(
         description="The temperature to use for token generation.",
         default=defs.LOCAL_SEARCH_LLM_TEMPERATURE,
     )
-    top_p: float | None = Field(
+    top_p: float = Field(
         description="The top-p value to use for token generation.",
         default=defs.LOCAL_SEARCH_LLM_TOP_P,
     )
-    n: int | None = Field(
+    n: int = Field(
         description="The number of completions to generate.",
         default=defs.LOCAL_SEARCH_LLM_N,
     )

graphrag/config/models/text_embedding_config.py

@@ -27,7 +27,7 @@ class TextEmbeddingConfig(BaseModel):
     names: list[str] = Field(
         description="The specific embeddings to perform.", default=[]
     )
-    vector_store: dict | None = Field(
+    vector_store: dict = Field(
         description="The vector storage configuration", default=defs.VECTOR_STORE_DICT
     )
     strategy: dict | None = Field(

graphrag/index/input/csv.py

@@ -33,7 +33,7 @@ async def load_file(path: str, group: dict | None) -> pd.DataFrame:
         if group is None:
             group = {}
         buffer = BytesIO(await storage.get(path, as_bytes=True))
-        data = pd.read_csv(buffer, encoding=config.encoding or "latin-1")
+        data = pd.read_csv(buffer, encoding=config.encoding)
         additional_keys = group.keys()
         if len(additional_keys) > 0:
             data[[*additional_keys]] = data.apply(