AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-14 06:45:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

DRAFT: Updated python and http api references (#2973)

Browse Source 
### What problem does this PR solve?


### Type of change

- [x] Documentation Update
This commit is contained in:
writinwaters 2024-10-22 17:10:23 +08:00 committed by GitHub
parent 445dce4363
commit 91ea559f9e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 103 additions and 89 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

102
api/http_api_reference.md
View File

@ -20,7 +20,7 @@ Creates a dataset.
### Request ### Request
- Method: POST - Method: POST
- URL: `http://{address}/api/v1/dataset` - URL: `/api/v1/dataset`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -163,7 +163,7 @@ Deletes datasets by ID.
### Request ### Request
- Method: DELETE - Method: DELETE
- URL: `http://{address}/api/v1/dataset` - URL: `/api/v1/dataset`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -219,7 +219,7 @@ Updates configurations for a specified dataset.
### Request ### Request
- Method: PUT - Method: PUT
- URL: `http://{address}/api/v1/dataset/{dataset_id}` - URL: `/api/v1/dataset/{dataset_id}`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -243,8 +243,6 @@ curl --request PUT \
--data '{ --data '{
"name": "test", "name": "test",
"embedding_model": "BAAI/bge-zh-v1.5", "embedding_model": "BAAI/bge-zh-v1.5",
"chunk_count": 0,
"document_count": 0,
"parse_method": "naive" "parse_method": "naive"
}' }'
``` ```
@ -293,14 +291,12 @@ An error response includes a JSON object like the following:
**GET** `/api/v1/dataset?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}` **GET** `/api/v1/dataset?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}`
Lists all datasets????? Lists datasets.
Retrieves a list of datasets.
### Request ### Request
- Method: GET - Method: GET
- URL: `http://{address}/api/v1/dataset?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}` - URL: `/api/v1/dataset?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}`
- Headers: - Headers:
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -407,10 +403,10 @@ Uploads documents to a specified dataset.
- Method: POST - Method: POST
- URL: `/api/v1/dataset/{dataset_id}/document` - URL: `/api/v1/dataset/{dataset_id}/document`
- Headers: - Headers:
- 'Content-Type: multipart/form-data' - `'Content-Type: multipart/form-data'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
- Form: - Form:
- 'file=@{FILE_PATH}' - `'file=@{FILE_PATH}'`
#### Request example #### Request example
@ -425,9 +421,9 @@ curl --request POST \
#### Request parameters #### Request parameters
- `"dataset_id"`: (*Path parameter*) - `"dataset_id"`: (*Path parameter*)
The dataset ID. The ID of the dataset to which the documents will be uploaded.
- `"file"`: (*Body parameter*) - `"file"`: (*Body parameter*)
The file to upload. The document???? to upload.
### Response ### Response
@ -459,25 +455,25 @@ Updates configurations for a specified document.
### Request ### Request
- Method: PUT - Method: PUT
- URL: `http://{address}/api/v1/dataset/{dataset_id}/document/{document_id}` - URL: `/api/v1/dataset/{dataset_id}/document/{document_id}`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
- Body: - Body:
- `name`:`string` - `"name"`:`string`
- `parser_method`:`string` - `"chunk_method"`:`string`
- `parser_config`:`dict` - `"parser_config"`:`dict`
#### Request example #### Request example
```bash ```bash
curl --request PUT \ curl --request PUT \
--url http://{address}/api/v1/dataset/{dataset_id}/info/{document_id} \ --url http://{address}/api/v1/dataset/{dataset_id}/info/{document_id} \
--header 'Authorization: Bearer {YOUR_ACCESS TOKEN}' \ --header 'Authorization: Bearer {YOUR_API_KEY}' \
--header 'Content-Type: application/json' \ --header 'Content-Type: application/json' \
--data '{ --data '{
"name": "manual.txt", "name": "manual.txt",
"parser_method": "manual", "chunk_method": "manual",
"parser_config": {"chunk_token_count": 128, "delimiter": "\n!?。；！？", "layout_recognize": true, "task_page_size": 12} "parser_config": {"chunk_token_count": 128, "delimiter": "\n!?。；！？", "layout_recognize": true, "task_page_size": 12}
}' }'
@ -485,8 +481,24 @@ curl --request PUT \
#### Request parameters #### Request parameters
- `"parser_method"`: (*Body parameter*) - `"name"`: (*Body parameter*), `string`
Method used to parse the document. - `"chunk_method"`: (*Body parameter*), `string`
The parsing method to apply to the document.
- `"naive"`: General
- `"manual`: Manual
- `"qa"`: Q&A
- `"table"`: Table
- `"paper"`: Paper
- `"book"`: Book
- `"laws"`: Laws
- `"presentation"`: Presentation
- `"picture"`: Picture
- `"one"`: One
- `"knowledge_graph"`: Knowledge Graph
- `"email"`: Email
-
### Returns
- `"parser_config"`: (*Body parameter*) - `"parser_config"`: (*Body parameter*)
Configuration object for the parser. Configuration object for the parser.
@ -525,7 +537,7 @@ Downloads a document from a specified dataset.
### Request ### Request
- Method: GET - Method: GET
- URL: `http://{address}/api/v1/dataset/{dataset_id}/document/{document_id}` - URL: `/api/v1/dataset/{dataset_id}/document/{document_id}`
- Headers: - Headers:
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
- Output: - Output:
@ -570,7 +582,7 @@ An error response includes a JSON object like the following:
**GET** `/api/v1/dataset/{dataset_id}/info?offset={offset}&limit={limit}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}` **GET** `/api/v1/dataset/{dataset_id}/info?offset={offset}&limit={limit}&orderby={orderby}&desc={desc}&keywords={keywords}&id={document_id}`
Retrieves a list of documents from a specified dataset. Lists documents in a specified dataset.
### Request ### Request
@ -670,7 +682,7 @@ Deletes documents by ID.
### Request ### Request
- Method: DELETE - Method: DELETE
- URL: `http://{address}/api/v1/dataset/{dataset_id}/document` - URL: `/api/v1/dataset/{dataset_id}/document`
- Headers: - Headers:
- `'Content-Type: application/json'` - `'Content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -724,7 +736,7 @@ Parses documents in a specified dataset.
### Request ### Request
- Method: POST - Method: POST
- URL: `http://{address}/api/v1/dataset/{dataset_id}/chunk ` - URL: `/api/v1/dataset/{dataset_id}/chunk `
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- 'Authorization: Bearer {YOUR_API_KEY}' - 'Authorization: Bearer {YOUR_API_KEY}'
@ -777,7 +789,7 @@ Stops parsing specified documents.
### Request ### Request
- Method: DELETE - Method: DELETE
- URL: `http://{address}/api/v1/dataset/{dataset_id}/chunk` - URL: `/api/v1/dataset/{dataset_id}/chunk`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -831,7 +843,7 @@ Adds a chunk to a specified document in a specified dataset.
### Request ### Request
- Method: POST - Method: POST
- URL: `http://{address}/api/v1/dataset/{dataset_id}/document/{document_id}/chunk` - URL: `/api/v1/dataset/{dataset_id}/document/{document_id}/chunk`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -896,12 +908,12 @@ An error response includes a JSON object like the following:
**GET** `/api/v1/dataset/{dataset_id}/document/{document_id}/chunk?keywords={keywords}&offset={offset}&limit={limit}&id={id}` **GET** `/api/v1/dataset/{dataset_id}/document/{document_id}/chunk?keywords={keywords}&offset={offset}&limit={limit}&id={id}`
Retrieves a list of chunks from a specified document in a specified dataset. Lists chunks in a specified document.
### Request ### Request
- Method: GET - Method: GET
- URL: `http://{address}/api/v1/dataset/{dataset_id}/document/{document_id}/chunk?keywords={keywords}&offset={offset}&limit={limit}&id={id}` - URL: `/api/v1/dataset/{dataset_id}/document/{document_id}/chunk?keywords={keywords}&offset={offset}&limit={limit}&id={id}`
- Headers: - Headers:
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -992,7 +1004,7 @@ Deletes chunks by ID.
### Request ### Request
- Method: DELETE - Method: DELETE
- URL: `http://{address}/api/v1/dataset/{dataset_id}/document/{document_id}/chunk` - URL: `/api/v1/dataset/{dataset_id}/document/{document_id}/chunk`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1046,7 +1058,7 @@ Updates content or configurations for a specified chunk.
### Request ### Request
- Method: PUT - Method: PUT
- URL: `http://{address}/api/v1/dataset/{dataset_id}/document/{document_id}/chunk/{chunk_id}` - URL: `/api/v1/dataset/{dataset_id}/document/{document_id}/chunk/{chunk_id}`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1102,12 +1114,12 @@ An error response includes a JSON object like the following:
**GET** `/api/v1/retrieval` **GET** `/api/v1/retrieval`
Retrieval test of a dataset Retrieves chunks from specified datasets.
### Request ### Request
- Method: POST - Method: POST
- URL: `http://{address}/api/v1/retrieval` - URL: `/api/v1/retrieval`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1252,7 +1264,7 @@ Creates a chat assistant.
### Request ### Request
- Method: POST - Method: POST
- URL: `http://{address}/api/v1/chat` - URL: `/api/v1/chat`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1486,7 +1498,7 @@ Updates configurations for a specified chat assistant.
### Request ### Request
- Method: PUT - Method: PUT
- URL: `http://{address}/api/v1/chat/{chat_id}` - URL: `/api/v1/chat/{chat_id}`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1538,7 +1550,7 @@ Deletes chat assistants by ID.
### Request ### Request
- Method: DELETE - Method: DELETE
- URL: `http://{address}/api/v1/chat` - URL: `/api/v1/chat`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1586,16 +1598,16 @@ An error response includes a JSON object like the following:
--- ---
## List chats (INCONSISTENT WITH THE PYTHON API) ## List chats
**GET** `/api/v1/chat?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}` **GET** `/api/v1/chat?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={chat_name}&id={chat_id}`
Retrieves a list of chat assistants. Lists chat assistants.
### Request ### Request
- Method: GET - Method: GET
- URL: `http://{address}/api/v1/chat?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}` - URL: `/api/v1/chat?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}`
- Headers: - Headers:
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1732,7 +1744,7 @@ Create a chat session.
### Request ### Request
- Method: POST - Method: POST
- URL: `http://{address}/api/v1/chat/{chat_id}/session` - URL: `/api/v1/chat/{chat_id}/session`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1827,7 +1839,7 @@ Update a chat session
### Request ### Request
- Method: PUT - Method: PUT
- URL: `http://{address}/api/v1/chat/{chat_id}/session/{session_id}` - URL: `/api/v1/chat/{chat_id}/session/{session_id}`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1882,7 +1894,7 @@ Lists sessions associated with a specified????????????? chat assistant.
### Request ### Request
- Method: GET - Method: GET
- URL: `http://{address}/api/v1/chat/{chat_id}/session?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}` - URL: `/api/v1/chat/{chat_id}/session?page={page}&page_size={page_size}&orderby={orderby}&desc={desc}&name={dataset_name}&id={dataset_id}`
- Headers: - Headers:
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -1967,7 +1979,7 @@ Deletes sessions by ID.
### Request ### Request
- Method: DELETE - Method: DELETE
- URL: `http://{address}/api/v1/chat/{chat_id}/session` - URL: `/api/v1/chat/{chat_id}/session`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`
@ -2023,7 +2035,7 @@ Asks a question to start a conversation.
### Request ### Request
- Method: POST - Method: POST
- URL: `http://{address}/api/v1/chat/{chat_id}/completion` - URL: `/api/v1/chat/{chat_id}/completion`
- Headers: - Headers:
- `'content-Type: application/json'` - `'content-Type: application/json'`
- `'Authorization: Bearer {YOUR_API_KEY}'` - `'Authorization: Bearer {YOUR_API_KEY}'`

90
api/python_api_reference.md
View File

@ -17,10 +17,9 @@ RAGFlow.create_dataset(
name: str, name: str,
avatar: str = "", avatar: str = "",
description: str = "", description: str = "",
embedding_model: str = "BAAI/bge-zh-v1.5",
language: str = "English", language: str = "English",
permission: str = "me", permission: str = "me",
document_count: int = 0,
chunk_count: int = 0,
chunk_method: str = "naive", chunk_method: str = "naive",
parser_config: DataSet.ParserConfig = None parser_config: DataSet.ParserConfig = None
) -> DataSet ) -> DataSet
@ -143,7 +142,7 @@ RAGFlow.list_datasets(
) -> list[DataSet] ) -> list[DataSet]
``` ```
Retrieves a list of datasets. Lists datasets.
### Parameters ### Parameters
@ -296,7 +295,7 @@ Updates configurations for the current document.
A dictionary representing the attributes to update, with the following keys: A dictionary representing the attributes to update, with the following keys:
- `"name"`: `str` The name of the document to update. - `"display_name"`: `str` The name of the document to update.
- `"parser_config"`: `dict[str, Any]` The parsing configuration for the document: - `"parser_config"`: `dict[str, Any]` The parsing configuration for the document:
- `"chunk_token_count"`: Defaults to `128`. - `"chunk_token_count"`: Defaults to `128`.
- `"layout_recognize"`: Defaults to `True`. - `"layout_recognize"`: Defaults to `True`.
@ -370,7 +369,7 @@ print(doc)
Dataset.list_documents(id:str =None, keywords: str=None, offset: int=0, limit:int = 1024,order_by:str = "create_time", desc: bool = True) -> list[Document] Dataset.list_documents(id:str =None, keywords: str=None, offset: int=0, limit:int = 1024,order_by:str = "create_time", desc: bool = True) -> list[Document]
``` ```
Retrieves a list of documents from the current dataset. Lists documents in the current dataset.
### Parameters ### Parameters
@ -388,7 +387,7 @@ The starting index for the documents to retrieve. Typically used in confunction
#### limit: `int` #### limit: `int`
The maximum number of documents to retrieve. Defaults to `1024`. A value of `-1` indicates that all documents should be returned. The maximum number of documents to retrieve. Defaults to `1024`.
#### orderby: `str` #### orderby: `str`
@ -412,7 +411,7 @@ A `Document` object contains the following attributes:
- `name`: The document name. Defaults to `""`. - `name`: The document name. Defaults to `""`.
- `thumbnail`: The thumbnail image of the document. Defaults to `None`. - `thumbnail`: The thumbnail image of the document. Defaults to `None`.
- `knowledgebase_id`: The dataset ID associated with the document. Defaults to `None`. - `knowledgebase_id`: The dataset ID associated with the document. Defaults to `None`.
- `chunk_method` The chunk method name. Defaults to `""`. ?????naive?????? - `chunk_method` The chunk method name. Defaults to `"naive"`.
- `parser_config`: `ParserConfig` Configuration object for the parser. Defaults to `{"pages": [[1, 1000000]]}`. - `parser_config`: `ParserConfig` Configuration object for the parser. Defaults to `{"pages": [[1, 1000000]]}`.
- `source_type`: The source type of the document. Defaults to `"local"`. - `source_type`: The source type of the document. Defaults to `"local"`.
- `type`: Type or category of the document. Defaults to `""`. Reserved for future use. - `type`: Type or category of the document. Defaults to `""`. Reserved for future use.
@ -425,7 +424,7 @@ A `Document` object contains the following attributes:
- `process_begin_at`: `datetime` The start time of document processing. Defaults to `None`. - `process_begin_at`: `datetime` The start time of document processing. Defaults to `None`.
- `process_duation`: `float` Duration of the processing in seconds. Defaults to `0.0`. - `process_duation`: `float` Duration of the processing in seconds. Defaults to `0.0`.
- `run`: `str` The document's processing status: - `run`: `str` The document's processing status:
- `"0"`: UNSTART (default) - `"0"`: UNSTART (default) ?????????
- `"1"`: RUNNING - `"1"`: RUNNING
- `"2"`: CANCEL - `"2"`: CANCEL
- `"3"`: DONE - `"3"`: DONE
@ -506,9 +505,9 @@ The IDs of the documents to parse.
rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380") rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
dataset = rag_object.create_dataset(name="dataset_name") dataset = rag_object.create_dataset(name="dataset_name")
documents = [ documents = [
{'name': 'test1.txt', 'blob': open('./test_data/test1.txt',"rb").read()}, {'display_name': 'test1.txt', 'blob': open('./test_data/test1.txt',"rb").read()},
{'name': 'test2.txt', 'blob': open('./test_data/test2.txt',"rb").read()}, {'display_name': 'test2.txt', 'blob': open('./test_data/test2.txt',"rb").read()},
{'name': 'test3.txt', 'blob': open('./test_data/test3.txt',"rb").read()} {'display_name': 'test3.txt', 'blob': open('./test_data/test3.txt',"rb").read()}
] ]
dataset.upload_documents(documents) dataset.upload_documents(documents)
documents = dataset.list_documents(keywords="test") documents = dataset.list_documents(keywords="test")
@ -546,9 +545,9 @@ The IDs of the documents for which parsing should be stopped.
rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380") rag_object = RAGFlow(api_key="<YOUR_API_KEY>", base_url="http://<YOUR_BASE_URL>:9380")
dataset = rag_object.create_dataset(name="dataset_name") dataset = rag_object.create_dataset(name="dataset_name")
documents = [ documents = [
{'name': 'test1.txt', 'blob': open('./test_data/test1.txt',"rb").read()}, {'display_name': 'test1.txt', 'blob': open('./test_data/test1.txt',"rb").read()},
{'name': 'test2.txt', 'blob': open('./test_data/test2.txt',"rb").read()}, {'display_name': 'test2.txt', 'blob': open('./test_data/test2.txt',"rb").read()},
{'name': 'test3.txt', 'blob': open('./test_data/test3.txt',"rb").read()} {'display_name': 'test3.txt', 'blob': open('./test_data/test3.txt',"rb").read()}
] ]
dataset.upload_documents(documents) dataset.upload_documents(documents)
documents = dataset.list_documents(keywords="test") documents = dataset.list_documents(keywords="test")
@ -566,7 +565,7 @@ print("Async bulk parsing cancelled.")
## Add chunk ## Add chunk
```python ```python
Document.add_chunk(content:str) -> Chunk ????????????????????? Document.add_chunk(content:str, important_keywords:list[str] = []) -> Chunk
``` ```
Adds a chunk to the current document. Adds a chunk to the current document.
@ -577,7 +576,7 @@ Adds a chunk to the current document.
The text content of the chunk. The text content of the chunk.
#### important_keywords: `list[str]` ?????????????????????? #### important_keywords: `list[str]`
The key terms or phrases to tag with the chunk. The key terms or phrases to tag with the chunk.
@ -588,7 +587,7 @@ The key terms or phrases to tag with the chunk.
A `Chunk` object contains the following attributes: A `Chunk` object contains the following attributes:
- `id`: `str` - `id`: `str`
- `content`: `str` Content of the chunk. - `content`: `str` Content of the chunk.
- `important_keywords`: `list[str]` A list of key terms or phrases to tag with the chunk. - `important_keywords`: `list[str]` A list of key terms or phrases to tag with the chunk.
- `create_time`: `str` The time when the chunk was created (added to the document). - `create_time`: `str` The time when the chunk was created (added to the document).
@ -596,9 +595,9 @@ A `Chunk` object contains the following attributes:
- `knowledgebase_id`: `str` The ID of the associated dataset. - `knowledgebase_id`: `str` The ID of the associated dataset.
- `document_name`: `str` The name of the associated document. - `document_name`: `str` The name of the associated document.
- `document_id`: `str` The ID of the associated document. - `document_id`: `str` The ID of the associated document.
- `available`: `int`???? The chunk's availability status in the dataset. Value options: - `available`: `bool` The chunk's availability status in the dataset. Value options:
- `0`: Unavailable - `False`: Unavailable
- `1`: Available - `True`: Available
### Examples ### Examples
@ -619,26 +618,26 @@ chunk = doc.add_chunk(content="xxxxxxx")
## List chunks ## List chunks
```python ```python
Document.list_chunks(keywords: str = None, offset: int = 0, limit: int = -1, id : str = None) -> list[Chunk] Document.list_chunks(keywords: str = None, offset: int = 1, limit: int = 1024, id : str = None) -> list[Chunk]
``` ```
Retrieves a list of chunks from the current document. Lists chunks in the current document.
### Parameters ### Parameters
#### keywords: `str` #### keywords: `str`
The keywords used to match chunk content. Defaults to `None` The keywords used to match chunk content. Defaults to `None`
#### offset: `int` #### offset: `int`
The starting index for the chunks to retrieve. Defaults to `1`?????? The starting index for the chunks to retrieve. Defaults to `1`.
#### limit #### limit: `int`
The maximum number of chunks to retrieve. Default: `30`????????? The maximum number of chunks to retrieve. Default: `1024`
#### id #### id: `str`
The ID of the chunk to retrieve. Default: `None` The ID of the chunk to retrieve. Default: `None`
@ -713,9 +712,9 @@ A dictionary representing the attributes to update, with the following keys:
- `"content"`: `str` Content of the chunk. - `"content"`: `str` Content of the chunk.
- `"important_keywords"`: `list[str]` A list of key terms or phrases to tag with the chunk. - `"important_keywords"`: `list[str]` A list of key terms or phrases to tag with the chunk.
- `"available"`: `int` The chunk's availability status in the dataset. Value options: - `"available"`: `bool` The chunk's availability status in the dataset. Value options:
- `0`: Unavailable - `False`: Unavailable
- `1`: Available - `True`: Available
### Returns ### Returns
@ -741,10 +740,10 @@ chunk.update({"content":"sdfx..."})
## Retrieve chunks ## Retrieve chunks
```python ```python
RAGFlow.retrieve(question:str="", datasets:list[str]=None, document=list[str]=None, offset:int=1, limit:int=30, similarity_threshold:float=0.2, vector_similarity_weight:float=0.3, top_k:int=1024,rerank_id:str=None,keyword:bool=False,higlight:bool=False) -> list[Chunk] RAGFlow.retrieve(question:str="", datasets:list[str]=None, document=list[str]=None, offset:int=1, limit:int=1024, similarity_threshold:float=0.2, vector_similarity_weight:float=0.3, top_k:int=1024,rerank_id:str=None,keyword:bool=False,higlight:bool=False) -> list[Chunk]
``` ```
??????? Retrieves chunks from specified datasets.
### Parameters ### Parameters
@ -752,21 +751,21 @@ RAGFlow.retrieve(question:str="", datasets:list[str]=None, document=list[str]=No
The user query or query keywords. Defaults to `""`. The user query or query keywords. Defaults to `""`.
#### datasets: `list[str]`, *Required*????? #### datasets: `list[str]`, *Required*
The datasets to search from. The datasets to search from.
#### document: `list[str]` #### document: `list[str]`
The documents to search from. `None` means no limitation. Defaults to `None`. The documents to search from. Defaults to `None`.
#### offset: `int` #### offset: `int`
The starting index for the documents to retrieve. Defaults to `0`??????. The starting index for the documents to retrieve. Defaults to `1`.
#### limit: `int` #### limit: `int`
The maximum number of chunks to retrieve. Defaults to `6`.??????????????? The maximum number of chunks to retrieve. Defaults to `1024`.
#### Similarity_threshold: `float` #### Similarity_threshold: `float`
@ -786,14 +785,17 @@ The ID of the rerank model. Defaults to `None`.
#### keyword: `bool` #### keyword: `bool`
Indicates whether keyword-based matching is enabled: Indicates whether to enable keyword-based matching:
- `True`: Enabled. - `True`: Enable keyword-based matching.
- `False`: Disabled (default). - `False`: Disable keyword-based matching (default).
#### highlight: `bool` #### highlight: `bool`
Specifying whether to enable highlighting of matched terms in the results (True) or not (False). Specifying whether to enable highlighting of matched terms in the results:
- `True`: Enable highlighting of matched terms.
- `False`: Disable highlighting of matched terms (default).
### Returns ### Returns
@ -849,15 +851,15 @@ Creates a chat assistant.
The following shows the attributes of a `Chat` object: The following shows the attributes of a `Chat` object:
#### name: `str`, *Required*???????? #### name: `str`, *Required*
The name of the chat assistant. Defaults to `"assistant"`. The name of the chat assistant..
#### avatar: `str` #### avatar: `str`
Base64 encoding of the avatar. Defaults to `""`. Base64 encoding of the avatar. Defaults to `""`.
#### knowledgebases: `list[str]` #### knowledgebases: `list[str]`
The IDs of the associated datasets. Defaults to `[""]`. The IDs of the associated datasets. Defaults to `[""]`.
@ -1016,7 +1018,7 @@ RAGFlow.list_chats(
) -> list[Chat] ) -> list[Chat]
``` ```
Retrieves a list of chat assistants. Lists chat assistants.
### Parameters ### Parameters