RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
docs(api): fix dataset parse_type examples and selection rules (#21333)
jay777219cb5539c0118
diff --git a/docs/references/http_api_reference.md b/docs/references/http_api_reference.mdindex a3706c70f6..49ab9f01be 100644--- a/docs/references/http_api_reference.md+++ b/docs/references/http_api_reference.md@@ -542,12 +542,13 @@ Creates a dataset.- `"language"`: `string`- `"embedding_model"`: `string`- `"permission"`: `string`+ - `"parser_id"`: `string`- `"chunk_method"`: `string`- `"parser_config"`: `object`- `"parse_type"`: `int`- `"pipeline_id"`: `string`-##### A basic request example+##### A request example creating a built-in general dataset```bashcurl --request POST \@@ -555,7 +556,10 @@ curl --request POST \--header 'Content-Type: application/json' \--header 'Authorization: Bearer <YOUR_API_KEY>' \--data '{- "name": "test_1"+ "name": "test_1",+ "language": "English",+ "parse_type": 1,+ "parser_id": "general"}'```@@ -573,7 +577,7 @@ curl --request POST \--data '{"name": "test-sdk","language": "English",- "parse_type": <NUMBER_OF_PARSERS_IN_YOUR_PARSER_COMPONENT>,+ "parse_type": 2,"pipeline_id": "<PIPELINE_ID_32_HEX>"}'```@@ -608,8 +612,24 @@ curl --request POST \- `"me"`: (Default) Only you can manage the dataset.- `"team"`: All team members can manage the dataset.+- `"parser_id"`: `enum<string>`+ The built-in parser to use. Required when `"parse_type"` is `1`.+ - `"general"`: General (default)+ - `"book"`: Book+ - `"email"`: Email+ - `"laws"`: Laws+ - `"manual"`: Manual+ - `"one"`: One+ - `"paper"`: Paper+ - `"picture"`: Picture+ - `"presentation"`: Presentation+ - `"qa"`: Q&A+ - `"table"`: Table+ - `"tag"`: Tag+ - Must not be included when `"parse_type"` is `2`.+- `"chunk_method"`: `enum<string>`- The default chunk method of the dataset to create. Mutually exclusive with `"parse_type"` and `"pipeline_id"`. If you set `"chunk_method"`, do not include `"parse_type"` or `"pipeline_id"`.+ Legacy alias of `"parser_id"` kept for Python-backend compatibility. The Go backend creates datasets with `"parser_id"` instead; do not send `"chunk_method"` together with `"parse_type"` or `"pipeline_id"`.Available options:- `"naive"`: General (default)- `"book"`: Book@@ -625,8 +645,8 @@ curl --request POST \- `"tag"`: Tag- `"parser_config"`: `object`- The configuration settings for the dataset parser. The attributes in this JSON object vary with the selected `"chunk_method"`:- - If `"chunk_method"` is `"naive"`, the `"parser_config"` object contains the following attributes:+ The configuration settings for the dataset parser. The attributes in this JSON object vary with the selected `"parser_id"`:+ - If `"parser_id"` is `"general"` (`"naive"` alias), the `"parser_config"` object contains the following attributes:- `"auto_keywords"`: `int`- Defaults to `0`- Minimum: `0`@@ -658,23 +678,21 @@ curl --request POST \- `"children_delimiter"`: `string` The delimiter used to split a parent chunk into child chunks. Only takes effect when `"use_parent_child"` is `true`. Defaults to `"\n"`.- `"parse_type"`: `int`- The ingestion pipeline parse type identifier, i.e., the number of parsers in your **Parser** component.- - Required (along with `"pipeline_id"`) if specifying an ingestion pipeline.- - Must not be included when `"chunk_method"` is specified.+ How the dataset selects its parser: `1` = built-in (`"parser_id"`), `2` = ingestion pipeline (`"pipeline_id"`).+ - Required. Use `1` together with `"parser_id"`, or `2` together with `"pipeline_id"`.+ - Do not mix the two options.- `"pipeline_id"`: `string`The ingestion pipeline ID. Can be found in the corresponding URL in the RAGFlow UI.- - Required (along with `"parse_type"`) if specifying an ingestion pipeline.+ - Required (along with `"parse_type": 2`) if specifying an ingestion pipeline.- Must be a 32-character lowercase hexadecimal string, e.g., `"d0bebe30ae2211f0970942010a8e0005"`.- - Must not be included when `"chunk_method"` is specified.+ - Must not be included when `"parse_type"` is `1`.:::caution WARNINGYou can choose either of the following ingestion options when creating a dataset, but *not* both:-- Use a built-in chunk method -- specify `"chunk_method"` (optionally with `"parser_config"`).-- Use an ingestion pipeline -- specify both `"parse_type"` and `"pipeline_id"`.--If none of `"chunk_method"`, `"parse_type"`, or `"pipeline_id"` are provided, the system defaults to `chunk_method = "naive"`.+- Use a built-in parser -- specify `"parse_type": 1` with `"parser_id"` (optionally with `"parser_config"`).+- Use an ingestion pipeline -- specify both `"parse_type": 2` and `"pipeline_id"`.:::#### Response