Fix variable typo (langgenius#8084)

api/configs/feature/__init__.py

@@ -46,7 +46,7 @@ class CodeExecutionSandboxConfig(BaseSettings):
     """
 
     CODE_EXECUTION_ENDPOINT: HttpUrl = Field(
-        description="endpoint URL of code execution servcie",
+        description="endpoint URL of code execution service",
         default="http://sandbox:8194",
     )
 
@@ -415,7 +415,7 @@ class MailConfig(BaseSettings):
     """
 
     MAIL_TYPE: Optional[str] = Field(
-        description="Mail provider type name, default to None, availabile values are `smtp` and `resend`.",
+        description="Mail provider type name, default to None, available values are `smtp` and `resend`.",
         default=None,
     )
 

api/controllers/console/datasets/datasets.py

@@ -18,7 +18,7 @@
 from core.provider_manager import ProviderManager
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.extractor.entity.extract_setting import ExtractSetting
-from core.rag.retrieval.retrival_methods import RetrievalMethod
+from core.rag.retrieval.retrieval_methods import RetrievalMethod
 from extensions.ext_database import db
 from fields.app_fields import related_app_list
 from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields

api/controllers/service_api/dataset/segment.py

@@ -67,7 +67,7 @@ def post(self, tenant_id, dataset_id, document_id):
             segments = SegmentService.multi_create_segment(args["segments"], document, dataset)
             return {"data": marshal(segments, segment_fields), "doc_form": document.doc_form}, 200
         else:
-            return {"error": "Segemtns is required"}, 400
+            return {"error": "Segments is required"}, 400
 
     def get(self, tenant_id, dataset_id, document_id):
         """Create single segment."""

api/core/helper/position_helper.py

@@ -79,7 +79,7 @@ def is_filtered(
         name_func: Callable[[Any], str],
 ) -> bool:
     """
-    Chcek if the object should be filtered out.
+    Check if the object should be filtered out.
     Overall logic: exclude > include > pin
     :param include_set: the set of names to be included
     :param exclude_set: the set of names to be excluded

api/core/indexing_runner.py

@@ -494,7 +494,7 @@ def _split_to_documents(self, text_docs: list[Document], splitter: TextSplitter,
                     hash = helper.generate_text_hash(document_node.page_content)
                     document_node.metadata['doc_id'] = doc_id
                     document_node.metadata['doc_hash'] = hash
-                    # delete Spliter character
+                    # delete Splitter character
                     page_content = document_node.page_content
                     if page_content.startswith(".") or page_content.startswith("。"):
                         page_content = page_content[1:]

api/core/llm_generator/prompts.py

@@ -87,7 +87,7 @@
 {{TASK_DESCRIPTION}}
 </task_description>
 Based on task description, please create a well-structured prompt template that another AI could use to consistently complete the task. The prompt template should include:
-- Do not inlcude <input> or <output> section and variables in the prompt, assume user will add them at their own will. 
+- Do not include <input> or <output> section and variables in the prompt, assume user will add them at their own will. 
 - Clear instructions for the AI that will be using this prompt, demarcated with <instructions> tags. The instructions should provide step-by-step directions on how to complete the task using the input variables. Also Specifies in the instructions that the output should not contain any xml tag. 
 - Relevant examples if needed to clarify the task further, demarcated with <example> tags. Do not include variables in the prompt. Give three pairs of input and output examples.   
 - Include other relevant sections demarcated with appropriate XML tags like <examples>, <instructions>.

api/core/model_runtime/docs/en_US/schema.md

@@ -52,7 +52,7 @@
     - `mode` (string)  voice model.（available for model type `tts`）
     - `name` (string)  voice model display name.（available for model type `tts`）
     - `language` (string)  the voice model supports languages.（available for model type `tts`）
-  - `word_limit` (int)  Single conversion word limit, paragraphwise by default（available for model type `tts`）
+  - `word_limit` (int)  Single conversion word limit, paragraph-wise by default（available for model type `tts`）
   - `audio_type` (string)  Support audio file extension format, e.g.：mp3,wav（available for model type `tts`）
   - `max_workers` (int)  Number of concurrent workers supporting text and audio conversion（available for model type`tts`）
   - `max_characters_per_chunk` (int) Maximum characters per chunk (available for model type `moderation`)
@@ -150,7 +150,7 @@
 
 - `input` (float) Input price, i.e., Prompt price
 - `output` (float) Output price, i.e., returned content price
-- `unit` (float) Pricing unit, e.g., if the price is meausred in 1M tokens, the corresponding token amount for the unit price is `0.000001`.
+- `unit` (float) Pricing unit, e.g., if the price is measured in 1M tokens, the corresponding token amount for the unit price is `0.000001`.
 - `currency` (string) Currency unit
 
 ### ProviderCredentialSchema

api/core/model_runtime/model_providers/__base/tts_model.py

@@ -13,7 +13,7 @@
 
 class TTSModel(AIModel):
     """
-    Model class for ttstext model.
+    Model class for TTS model.
     """
     model_type: ModelType = ModelType.TTS
 

api/core/model_runtime/model_providers/azure_openai/llm/llm.py

@@ -284,7 +284,7 @@ def _chat_generate(self, model: str, credentials: dict,
                 try:
                     schema = json.loads(json_schema)
                 except:
-                    raise ValueError(f"not currect json_schema format: {json_schema}")
+                    raise ValueError(f"not correct json_schema format: {json_schema}")
                 model_parameters.pop("json_schema")
                 model_parameters["response_format"] = {"type": "json_schema", "json_schema": schema}
             else:

api/core/model_runtime/model_providers/baichuan/llm/llm.py

@@ -37,7 +37,7 @@
 )
 
 
-class BaichuanLarguageModel(LargeLanguageModel):
+class BaichuanLanguageModel(LargeLanguageModel):
 
     def _invoke(
             self,

api/core/model_runtime/model_providers/baichuan/text_embedding/text_embedding.py

@@ -60,7 +60,7 @@ def _invoke(self, model: str, credentials: dict,
         token_usage = 0
 
         for chunk in chunks:
-            # embeding chunk
+            # embedding chunk
             chunk_embeddings, chunk_usage = self.embedding(
                 model=model,
                 api_key=api_key,

api/core/model_runtime/model_providers/bedrock/llm/llm.py

@@ -793,11 +793,11 @@ def _handle_generate_stream_response(self, model: str, credentials: dict, respon
     def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
         """
         Map model invoke error to unified error
-        The key is the ermd = genai.GenerativeModel(model)ror type thrown to the caller
-        The value is the md = genai.GenerativeModel(model)error type thrown by the model,
+        The key is the ermd = genai.GenerativeModel(model) error type thrown to the caller
+        The value is the md = genai.GenerativeModel(model) error type thrown by the model,
         which needs to be converted into a unified error type for the caller.
 
-        :return: Invoke emd = genai.GenerativeModel(model)rror mapping
+        :return: Invoke emd = genai.GenerativeModel(model) error mapping
         """
         return {
             InvokeConnectionError: [],

api/core/model_runtime/model_providers/bedrock/text_embedding/text_embedding.py

@@ -130,11 +130,11 @@ def validate_credentials(self, model: str, credentials: dict) -> None:
     def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
         """
         Map model invoke error to unified error
-        The key is the ermd = genai.GenerativeModel(model)ror type thrown to the caller
-        The value is the md = genai.GenerativeModel(model)error type thrown by the model,
+        The key is the ermd = genai.GenerativeModel(model) error type thrown to the caller
+        The value is the md = genai.GenerativeModel(model) error type thrown by the model,
         which needs to be converted into a unified error type for the caller.
 
-        :return: Invoke emd = genai.GenerativeModel(model)rror mapping
+        :return: Invoke emd = genai.GenerativeModel(model) error mapping
         """
         return {
             InvokeConnectionError: [],

api/core/model_runtime/model_providers/google/llm/llm.py

@@ -416,11 +416,11 @@ def _format_message_to_glm_content(self, message: PromptMessage) -> ContentType:
     def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
         """
         Map model invoke error to unified error
-        The key is the ermd = genai.GenerativeModel(model)ror type thrown to the caller
-        The value is the md = genai.GenerativeModel(model)error type thrown by the model,
+        The key is the ermd = genai.GenerativeModel(model) error type thrown to the caller
+        The value is the md = genai.GenerativeModel(model) error type thrown by the model,
         which needs to be converted into a unified error type for the caller.
 
-        :return: Invoke emd = genai.GenerativeModel(model)rror mapping
+        :return: Invoke emd = genai.GenerativeModel(model) error mapping
         """
         return {
             InvokeConnectionError: [

api/core/model_runtime/model_providers/minimax/llm/llm.py

@@ -86,7 +86,7 @@ def _num_tokens_from_messages(self, messages: list[PromptMessage], tools: list[P
             Calculate num tokens for minimax model
 
             not like ChatGLM, Minimax has a special prompt structure, we could not find a proper way
-            to caculate the num tokens, so we use str() to convert the prompt to string
+            to calculate the num tokens, so we use str() to convert the prompt to string
 
             Minimax does not provide their own tokenizer of adab5.5 and abab5 model
             therefore, we use gpt2 tokenizer instead

api/core/model_runtime/model_providers/novita/llm/llm.py

@@ -10,6 +10,7 @@
 class NovitaLargeLanguageModel(OAIAPICompatLargeLanguageModel):
 
     def _update_endpoint_url(self, credentials: dict):
+
         credentials['endpoint_url'] = "https://api.novita.ai/v3/openai"
         credentials['extra_headers'] = { 'X-Novita-Source': 'dify.ai' }
         return credentials

api/core/model_runtime/model_providers/oci/llm/llm.py

@@ -243,7 +243,7 @@ def _generate(self, model: str, credentials: dict,
         request_args["compartmentId"] = compartment_id
         request_args["servingMode"]["modelId"] = model
 
-        chathistory = []
+        chat_history = []
         system_prompts = []
         #if "meta.llama" in model:
         #    request_args["chatRequest"]["apiFormat"] = "GENERIC"
@@ -273,16 +273,16 @@ def _generate(self, model: str, credentials: dict,
                 if isinstance(message.content, str):
                     text = message.content
                 if isinstance(message, UserPromptMessage):
-                    chathistory.append({"role": "USER", "message": text})
+                    chat_history.append({"role": "USER", "message": text})
                 else:
-                    chathistory.append({"role": "CHATBOT", "message": text})
+                    chat_history.append({"role": "CHATBOT", "message": text})
                 if isinstance(message, SystemPromptMessage):
                     if isinstance(message.content, str):
                         system_prompts.append(message.content)
             args = {"apiFormat": "COHERE",
                     "preambleOverride": ' '.join(system_prompts),
                     "message": prompt_messages[-1].content,
-                    "chatHistory": chathistory, }
+                    "chatHistory": chat_history, }
             request_args["chatRequest"].update(args)
         elif model.startswith("meta"):
             #print("run meta " * 10)

api/core/model_runtime/model_providers/openai/llm/llm.py

@@ -552,7 +552,7 @@ def _chat_generate(self, model: str, credentials: dict,
                 try:
                     schema = json.loads(json_schema)
                 except:
-                    raise ValueError(f"not currect json_schema format: {json_schema}")
+                    raise ValueError(f"not correct json_schema format: {json_schema}")
                 model_parameters.pop("json_schema")
                 model_parameters["response_format"] = {"type": "json_schema", "json_schema": schema}
             else:

api/core/model_runtime/model_providers/tencent/speech2text/flash_recognizer.py

@@ -67,7 +67,7 @@ def set_reinforce_hotword(self, reinforce_hotword):
 
 class FlashRecognizer:
     """
-    reponse:
+    response:
     request_id        string
     status            Integer    
     message           String    
@@ -132,9 +132,9 @@ def _build_req_with_signature(self, secret_key, params, header):
         signstr = self._format_sign_string(query)
         signature = self._sign(signstr, secret_key)
         header["Authorization"] = signature
-        requrl = "https://"
-        requrl += signstr[4::]
-        return requrl
+        req_url = "https://"
+        req_url += signstr[4::]
+        return req_url
 
     def _create_query_arr(self, req):
         return {

api/core/model_runtime/model_providers/vertex_ai/llm/llm.py

@@ -695,11 +695,11 @@ def _format_message_to_glm_content(self, message: PromptMessage) -> glm.Content:
     def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
         """
         Map model invoke error to unified error
-        The key is the ermd = gml.GenerativeModel(model)ror type thrown to the caller
-        The value is the md = gml.GenerativeModel(model)error type thrown by the model,
+        The key is the ermd = gml.GenerativeModel(model) error type thrown to the caller
+        The value is the md = gml.GenerativeModel(model) error type thrown by the model,
         which needs to be converted into a unified error type for the caller.
 
-        :return: Invoke emd = gml.GenerativeModel(model)rror mapping
+        :return: Invoke emd = gml.GenerativeModel(model) error mapping
         """
         return {
             InvokeConnectionError: [

api/core/model_runtime/model_providers/zhipuai/zhipuai_sdk/core/_http_client.py

@@ -135,16 +135,16 @@ def _prepare_request(
             **kwargs,
         )
 
-    def _object_to_formfata(self, key: str, value: Data | Mapping[object, object]) -> list[tuple[str, str]]:
+    def _object_to_formdata(self, key: str, value: Data | Mapping[object, object]) -> list[tuple[str, str]]:
         items = []
 
         if isinstance(value, Mapping):
             for k, v in value.items():
-                items.extend(self._object_to_formfata(f"{key}[{k}]", v))
+                items.extend(self._object_to_formdata(f"{key}[{k}]", v))
             return items
         if isinstance(value, list | tuple):
             for v in value:
-                items.extend(self._object_to_formfata(key + "[]", v))
+                items.extend(self._object_to_formdata(key + "[]", v))
             return items
 
         def _primitive_value_to_str(val) -> str:
@@ -165,7 +165,7 @@ def _primitive_value_to_str(val) -> str:
 
     def _make_multipartform(self, data: Mapping[object, object]) -> dict[str, object]:
 
-        items = flatten([self._object_to_formfata(k, v) for k, v in data.items()])
+        items = flatten([self._object_to_formdata(k, v) for k, v in data.items()])
 
         serialized: dict[str, object] = {}
         for key, value in items:

api/core/rag/cleaner/unstructured/unstructured_non_ascii_chars_cleaner.py

@@ -8,5 +8,5 @@ def clean(self, content) -> str:
         """clean document content."""
         from unstructured.cleaners.core import clean_non_ascii_chars
 
-        # Returns "This text containsnon-ascii characters!"
+        # Returns "This text contains non-ascii characters!"
         return clean_non_ascii_chars(content)