pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added a list of supported models (#3214)

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

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change


- [x] Documentation Update
This commit is contained in:
writinwaters
2024-11-05 15:21:37 +08:00
committed by GitHub
parent 13053172cb
commit ab6e6019a7
4 changed files with 151 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
docs/references/http_api_reference.md
View File

@ -1,6 +1,5 @@
---
sidebar_position: 0
sidebar_position: 1
slug: /http_api_reference
---
@ -93,7 +92,7 @@ curl --request POST \
- `"picture"`: Picture
- `"one"`: One
- `"knowledge_graph"`: Knowledge Graph
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please note that Knowledge Graph consumes a large number of Tokens!
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
- `"email"`: Email
- `"parser_config"`: (*Body parameter*), `object`
@ -269,7 +268,9 @@ curl --request PUT \
- `"presentation"`: Presentation
- `"picture"`: Picture
- `"one"`:One
- `"knowledge_graph"`: Knowledge Graph
- `"email"`: Email
- `"knowledge_graph"`: Knowledge Graph
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
### Response
@ -318,7 +319,7 @@ curl --request GET \
- `page`: (*Filter parameter*)
Specifies the page on which the datasets will be displayed. Defaults to `1`.
- `page_size`: (*Filter parameter*)
The number of datasets on each page. Defaults to `1024`.
The number of datasets on each page. Defaults to `30`.
- `orderby`: (*Filter parameter*)
The field by which datasets should be sorted. Available options:
- `create_time` (default)
@ -524,7 +525,7 @@ curl --request PUT \
- `"picture"`: Picture
- `"one"`: One
- `"knowledge_graph"`: Knowledge Graph
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please note that Knowledge Graph consumes a large number of Tokens!
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
- `"email"`: Email
- `"parser_config"`: (*Body parameter*), `object`
The configuration settings for the dataset parser. The attributes in this JSON object vary with the selected `"chunk_method"`:
@ -645,7 +646,7 @@ curl --request GET \
- `page`: (*Filter parameter*), `integer`
Specifies the page on which the documents will be displayed. Defaults to `1`.
- `page_size`: (*Filter parameter*), `integer`
The maximum number of documents on each page. Defaults to `1024`.
The maximum number of documents on each page. Defaults to `30`.
- `orderby`: (*Filter parameter*), `string`
The field by which documents should be sorted. Available options:
- `create_time` (default)
@ -1245,7 +1246,7 @@ curl --request POST \
- `"page"`: (*Body parameter*), `integer`
Specifies the page on which the chunks will be displayed. Defaults to `1`.
- `"page_size"`: (*Body parameter*)
The maximum number of chunks on each page. Defaults to `1024`.
The maximum number of chunks on each page. Defaults to `30`.
- `"similarity_threshold"`: (*Body parameter*)
The minimum similarity score. Defaults to `0.2`.
- `"vector_similarity_weight"`: (*Body parameter*), `float`
@ -1628,7 +1629,7 @@ curl --request GET \
- `page`: (*Filter parameter*), `integer`
Specifies the page on which the chat assistants will be displayed. Defaults to `1`.
- `page_size`: (*Filter parameter*), `integer`
The number of chat assistants on each page. Defaults to `1024`.
The number of chat assistants on each page. Defaults to `30`.
- `orderby`: (*Filter parameter*), `string`
The attribute by which the results are sorted. Available options:
- `create_time` (default)
@ -1860,7 +1861,7 @@ curl --request GET \
- `page`: (*Filter parameter*), `integer`
Specifies the page on which the sessions will be displayed. Defaults to `1`.
- `page_size`: (*Filter parameter*), `integer`
The number of sessions on each page. Defaults to `1024`.
The number of sessions on each page. Defaults to `30`.
- `orderby`: (*Filter parameter*), `string`
The field by which sessions should be sorted. Available options:
- `create_time` (default)

37
docs/references/python_api_reference.md
View File

@ -1,5 +1,5 @@
from Demos.mmapfile_demo import page_sizefrom Demos.mmapfile_demo import page_sizesidebar_position: 1
---
sidebar_position: 2
slug: /python_api_reference
---
@ -58,7 +58,7 @@ A brief description of the dataset to create. Defaults to `""`.
The language setting of the dataset to create. Available options:
- `"English"` (Default)
- `"English"` (default)
- `"Chinese"`
#### permission
@ -80,7 +80,7 @@ The chunking method of the dataset to create. Available options:
- `"picture"`: Picture
- `"one"`: One
- `"knowledge_graph"`: Knowledge Graph
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please note that Knowledge Graph consumes a large number of Tokens!
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
- `"email"`: Email
#### parser_config
@ -160,7 +160,7 @@ rag_object.delete_datasets(ids=["id_1","id_2"])
```python
RAGFlow.list_datasets(
page: int = 1,
page_size: int = 1024,
page_size: int = 30,
orderby: str = "create_time",
desc: bool = True,
id: str = None,
@ -178,7 +178,7 @@ Specifies the page on which the datasets will be displayed. Defaults to `1`.
#### page_size: `int`
The number of datasets on each page. Defaults to `1024`.
The number of datasets on each page. Defaults to `30`.
#### orderby: `str`
@ -250,8 +250,9 @@ A dictionary representing the attributes to update, with the following keys:
- `"presentation"`: Presentation
- `"picture"`: Picture
- `"one"`: One
- `"email"`: Email
- `"knowledge_graph"`: Knowledge Graph
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please note that Knowledge Graph consumes a large number of Tokens!
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
### Returns
@ -334,7 +335,7 @@ A dictionary representing the attributes to update, with the following keys:
- `"picture"`: Picture
- `"one"`: One
- `"knowledge_graph"`: Knowledge Graph
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please note that Knowledge Graph consumes a large number of Tokens!
Ensure your LLM is properly configured on the **Settings** page before selecting this. Please also note that Knowledge Graph consumes a large number of Tokens!
- `"email"`: Email
- `"parser_config"`: `dict[str, Any]` The parsing configuration for the document. Its attributes vary based on the selected `"chunk_method"`:
- `"chunk_method"`=`"naive"`:
@ -413,7 +414,7 @@ print(doc)
## List documents
```python
Dataset.list_documents(id:str =None, keywords: str=None, page: int=1, page_size:int = 1024,order_by:str = "create_time", desc: bool = True) -> list[Document]
Dataset.list_documents(id:str =None, keywords: str=None, page: int=1, page_size:int = 30, order_by:str = "create_time", desc: bool = True) -> list[Document]
```
Lists documents in the current dataset.
@ -434,7 +435,7 @@ Specifies the page on which the documents will be displayed. Defaults to `1`.
#### page_size: `int`
The maximum number of documents on each page. Defaults to `1024`.
The maximum number of documents on each page. Defaults to `30`.
#### orderby: `str`
@ -689,7 +690,7 @@ chunk = doc.add_chunk(content="xxxxxxx")
## List chunks
```python
Document.list_chunks(keywords: str = None, page: int = 1, page_size: int = 1024, id : str = None) -> list[Chunk]
Document.list_chunks(keywords: str = None, page: int = 1, page_size: int = 30, id : str = None) -> list[Chunk]
```
Lists chunks in the current document.
@ -706,7 +707,7 @@ Specifies the page on which the chunks will be displayed. Defaults to `1`.
#### page_size: `int`
The maximum number of chunks on each page. Defaults to `1024`.
The maximum number of chunks on each page. Defaults to `30`.
#### id: `str`
@ -811,7 +812,7 @@ chunk.update({"content":"sdfx..."})
## Retrieve chunks
```python
RAGFlow.retrieve(question:str="", dataset_ids:list[str]=None, document_ids=list[str]=None, page:int=1, page_size: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]
RAGFlow.retrieve(question:str="", dataset_ids:list[str]=None, document_ids=list[str]=None, page:int=1, page_size: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]
```
Retrieves chunks from specified datasets.
@ -836,7 +837,7 @@ The starting index for the documents to retrieve. Defaults to `1`.
#### page_size: `int`
The maximum number of chunks to retrieve. Defaults to `1024`.
The maximum number of chunks to retrieve. Defaults to `30`.
#### Similarity_threshold: `float`
@ -1078,7 +1079,7 @@ rag_object.delete_chats(ids=["id_1","id_2"])
```python
RAGFlow.list_chats(
page: int = 1,
page_size: int = 1024,
page_size: int = 30,
orderby: str = "create_time",
desc: bool = True,
id: str = None,
@ -1096,7 +1097,7 @@ Specifies the page on which the chat assistants will be displayed. Defaults to `
#### page_size: `int`
The number of chat assistants on each page. Defaults to `1024`.
The number of chat assistants on each page. Defaults to `30`.
#### orderby: `str`
@ -1216,7 +1217,7 @@ session.update({"name": "updated_name"})
```python
Chat.list_sessions(
page: int = 1,
page_size: int = 1024,
page_size: int = 30,
orderby: str = "create_time",
desc: bool = True,
id: str = None,
@ -1234,7 +1235,7 @@ Specifies the page on which the sessions will be displayed. Defaults to `1`.
#### page_size: `int`
The number of sessions on each page. Defaults to `1024`.
The number of sessions on each page. Defaults to `30`.
#### orderby: `str`

66
docs/references/supported_models.mdx Normal file
View File

@ -0,0 +1,66 @@
---
sidebar_position: 0
slug: /supported_models
---
# Supported models
import APITable from '../../src/components/APITable';
A complete list of models supported by RAGFlow, which will continue to expand.
```mdx-code-block
<APITable>
```
| Provider | Chat | Embedding | Rerank | Multi-modal | ASR/STT | TTS |
| --------------------- | ------------------ | ------------------ | ------------------ | ------------------ | ------------------ | ------------------ |
| Anthropic | :heavy_check_mark: | | | | | |
| Azure-OpenAI | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | :heavy_check_mark: | |
| BAAI | | :heavy_check_mark: | :heavy_check_mark: | | | |
| BaiChuan | :heavy_check_mark: | :heavy_check_mark: | | | | |
| BaiduYiyan | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| Bedrock | :heavy_check_mark: | :heavy_check_mark: | | | | |
| cohere | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| DeepSeek | :heavy_check_mark: | | | | | |
| FastEmbed | | :heavy_check_mark: | | | | |
| Fish Audio | | | | | | :heavy_check_mark: |
| Gemini | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | | |
| Google Cloud | :heavy_check_mark: | | | | | |
| Groq | :heavy_check_mark: | | | | | |
| HuggingFace | :heavy_check_mark: | :heavy_check_mark: | | | | |
| Jina | | :heavy_check_mark: | :heavy_check_mark: | | | |
| LeptonAI | :heavy_check_mark: | | | | | |
| LocalAI | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | | |
| LM-Studio | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| MiniMax | :heavy_check_mark: | | | | | |
| Mistral | :heavy_check_mark: | :heavy_check_mark: | | | | |
| Moonshot | :heavy_check_mark: | | | :heavy_check_mark: | | |
| novita.ai | :heavy_check_mark: | | | | | |
| NVIDIA | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| Ollama | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | | |
| OpenAI | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
| OpenAI-API-Compatible | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| OpenRouter | :heavy_check_mark: | | | :heavy_check_mark: | | |
| PerfXCloud | :heavy_check_mark: | :heavy_check_mark: | | | | |
| Replicate | :heavy_check_mark: | :heavy_check_mark: | | | | |
| SILICONFLOW | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| StepFun | :heavy_check_mark: | | | | | |
| Tencent Hunyuan | :heavy_check_mark: | | | | | |
| Tencent Cloud | | | | | :heavy_check_mark: | |
| TogetherAI | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| Tongyi-Qianwen | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
| Upstage | :heavy_check_mark: | :heavy_check_mark: | | | | |
| VolcEngine | :heavy_check_mark: | | | | | |
| Voyage AI | | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | | |
| Xinference | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: |
| XunFei Spark | :heavy_check_mark: | | | | | :heavy_check_mark: |
| Youdao | | :heavy_check_mark: | :heavy_check_mark: | | | |
| ZHIPU-AI | :heavy_check_mark: | :heavy_check_mark: | | :heavy_check_mark: | | |
| 01.AI | :heavy_check_mark: | | | | | |
```mdx-code-block
</APITable>
```