AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-11 17:19:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added an FAQ (#5092)

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


### Type of change


- [x] Documentation Update
This commit is contained in:
writinwaters 2025-02-18 19:29:40 +08:00 committed by GitHub
parent 18e43831bc
commit 3cffadc7a2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
7 changed files with 61 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/guides/accelerate_question_answering.mdx
View File

@ -16,7 +16,7 @@ Please note that some of your settings may consume a significant amount of time.
- Use GPU to reduce embedding time.
- On the configuration page of your knowledge base, switch off **Use RAPTOR to enhance retrieval**.
- The **Knowledge Graph** chunk method (GraphRAG) is time-consuming.
- Extracting knowledge graph (GraphRAG) is time-consuming.
- Disable **Auto-keyword** and **Auto-question** on the configuration page of yor knowledge base, as both depend on the LLM.
## 2. Accelerate question answering

12
docs/guides/configure_knowledge_base/construct_knowledge_graph.md
View File

@ -44,23 +44,23 @@ The method to use to construct knowledge graph:
### Entity resolution
Whether to enable entity resolution. You can think of this as an entity deduplication switch. When enabled, the LLM will combine similar entities - e.g., '2025' and 'the year of 2025', or 'IT' and 'Information Technology' - to construct a more accurate graph.
Whether to enable entity resolution. You can think of this as an entity deduplication switch. When enabled, the LLM will combine similar entities - e.g., '2025' and 'the year of 2025', or 'IT' and 'Information Technology' - to construct a more effective graph.
- (Default) Disable entity resolution. This option consumes fewer tokens.
- Enable entity resolution.
- (Default) Disable entity resolution.
- Enable entity resolution. This option consumes more tokens.
### Community report generation
In a knowledge graph, a community is a cluster of entities linked by relationships. You can have the LLM generate an abstract for each community, known as a community report. See [here](https://www.microsoft.com/en-us/research/blog/graphrag-improving-global-search-via-dynamic-community-selection/) for more information. This indicates whether to generate community reports:
- Generate community reports.
- (Default) Do not generate community reports. This options consumes fewer tokens.
- Generate community reports. This option consumes more tokens.
- (Default) Do not generate community reports.
## Procedure
1. On the **Configuration** page of your knowledge base, switch on **Extract knowledge graph** or adjust its settings as needed, and click **Save** to confirm your changes.
- *The default GraphRAG configurations for your knowlege base are now set and files uploaded from this point onward will automatically use these settings during parsing.*
- *The default knowledge graph configurations for your knowlege base are now set and files uploaded from this point onward will automatically use these settings during parsing.*
- *Files parsed before this update will retain their original knowledge graph settings.*
2. The knowledge graph of your knowlege base does *not* automatically update *until* a newly uploaded file is parsed.

29
docs/references/faq.md
View File

@ -22,6 +22,35 @@ The "garbage in garbage out" status quo remains unchanged despite the fact that
---
### Where to find the version of RAGFlow? How to interprete it?
You can find the RAGFlow version number on the **System** page of the UI:
![Image](https://github.com/user-attachments/assets/20cf7213-2537-4e18-a88c-4dadf6228c6b)
If you build RAGFlow from source, the version number is also in the system log:
```
____ ___ ______ ______ __
/ __ \ / | / ____// ____// /____ _ __
/ /_/ // /| | / / __ / /_ / // __ \| | /| / /
/ _, _// ___ |/ /_/ // __/ / // /_/ /| |/ |/ /
/_/ |_|/_/ |_|\____//_/ /_/ \____/ |__/|__/
2025-02-18 10:10:43,835 INFO 1445658 RAGFlow version: v0.16.0-50-g6daae7f2 full
```
Where:
- `v0.16.0`: The officially published release.
- `50`: The number of git commits since the official release.
- `g6daae7f2`: `g` is the prefix, and `6daae7f2` is the first seven characters of the current commit ID.
- `full`/`slim`: The RAGFlow edition.
- `full`: The full RAGFlow edition.
- `slim`: The RAGFlow edition without embedding models and Python packages.
---
### Why does it take longer for RAGFlow to parse a document than LangChain?
We put painstaking effort into document pre-processing tasks like layout analysis, table structure recognition, and OCR (Optical Character Recognition) using our vision models. This contributes to the additional time required.

30
docs/references/http_api_reference.md
View File

@ -2178,10 +2178,12 @@ Creates a session with an agent.
- Body:
- the required parameters:`str`
- other parameters:
The parameters in the begin component.
The parameters set in the **Begin** component.
##### Request example
If `begin` component in the agent doesn't have required parameters:
If the **Begin** component in your agent does not have required parameters:
```bash
curl --request POST \
--url http://{address}/api/v1/agents/{agent_id}/sessions \
@ -2190,7 +2192,9 @@ curl --request POST \
--data '{
}'
```
If `begin` component in the agent has required parameters:
If the **Begin** component in your agent has required parameters:
```bash
curl --request POST \
--url http://{address}/api/v1/agents/{agent_id}/sessions \
@ -2201,7 +2205,9 @@ curl --request POST \
"file":"Who are you"
}'
```
If `begin` component in the agent has required file parameters:
If the **Begin** component in your agent has required file parameters:
```bash
curl --request POST \
--url http://{address}/api/v1/agents/{agent_id}/sessions?user_id={user_id} \
@ -2215,7 +2221,7 @@ curl --request POST \
- `agent_id`: (*Path parameter*)
The ID of the associated agent.
- `user_id`: (*Filter parameter*), string
The optional user-defined ID for parsing docs(especially images) when creating session while uploading files.
The optional user-defined ID for parsing docs (especially images) when creating a session while uploading files.
#### Response
@ -2367,7 +2373,7 @@ Asks a specified agent a question to start an AI-powered conversation.
- `"user_id"`: `string`(optional)
- other parameters: `string`
##### Request example
If the `begin` component doesn't have parameters, the following code will create a session.
Ifthe **Begin** component doesn't have parameters, the following code will create a session.
```bash
curl --request POST \
--url http://{address}/api/v1/agents/{agent_id}/completions \
@ -2377,7 +2383,7 @@ curl --request POST \
{
}'
```
If the `begin` component have parameters, the following code will create a session.
Ifthe **Begin** component have parameters, the following code will create a session.
```bash
curl --request POST \
--url http://{address}/api/v1/agents/{agent_id}/completions \
@ -2403,7 +2409,6 @@ curl --request POST \
}'
```
##### Request Parameters
- `agent_id`: (*Path parameter*), `string`
@ -2419,9 +2424,10 @@ curl --request POST \
- `"user_id"`: (*Body parameter*), `string`
The optional user-defined ID. Valid *only* when no `session_id` is provided.
- Other parameters: (*Body Parameter*)
The parameters in the begin component.
Parameters specified in the **Begin** component.
#### Response
success without `session_id` provided and with no parameters in the `begin` component:
success without `session_id` provided and with no parameters inthe **Begin** component:
```json
data:{
"code": 0,
@ -2439,7 +2445,7 @@ data:{
"data": true
}
```
Success without `session_id` provided and with parameters in the `begin` component:
Success without `session_id` provided and with parameters inthe **Begin** component:
```json
data:{
@ -2475,7 +2481,7 @@ data:{
}
data:
```
Success with parameters in the `begin` component:
Success with parameters inthe **Begin** component:
```json
data:{
"code": 0,

2
docs/references/python_api_reference.md
View File

@ -1461,7 +1461,7 @@ In streaming mode, not all responses include a reference, as this depends on the
##### question: `str`
The question to start an AI-powered conversation. If the `begin` component takes parameters, a question is not required.
The question to start an AI-powered conversation. Ifthe **Begin** component takes parameters, a question is not required.
##### stream: `bool`

2
docs/release_notes.md
View File

@ -14,7 +14,7 @@ Released on February 6, 2025.
### New features
- Supports DeepSeek R1 and DeepSeek V3.
- GraphRAG refactor: Knowledge graph is dynamically built on an entire knowledge base (dataset) rather than on an individual file, and automatically updated when files are added or removed.
- GraphRAG refactor: Knowledge graph is dynamically built on an entire knowledge base (dataset) rather than on an individual file, and automatically updated when files are added or removed. See [here](https://ragflow.io/docs/dev/construct_knowledge_graph).
- Adds an **Iteration** agent component and a **Research report generator** agent template.
- New UI language: Portuguese.
- Allows setting metadata for a specific file in a knowledge base to support AI-powered chats.

10
web/src/locales/en.ts
View File

@ -369,15 +369,15 @@ This procedure will improve precision of retrieval by adding more information to
addTag: 'Add tag',
useGraphRag: 'Extract knowledge graph',
useGraphRagTip:
'After files being chunked, all the chunks will be used for knowlege graph generation which helps inference of multi-hop and complex problems a lot.',
'Construct a knowledge graph over extracted file chunks to enhance multi-hop question answering.',
graphRagMethod: 'Method',
graphRagMethodTip: `Light: the entity and relation extraction prompt is from GitHub - HKUDS/LightRAG: "LightRAG: Simple and Fast Retrieval-Augmented Generation"</br>
General: the entity and relation extraction prompt is from GitHub - microsoft/graphrag: A modular graph-based Retrieval-Augmented Generation (RAG) system`,
graphRagMethodTip: `Light: (Default) Use prompts provided by github.com/HKUDS/LightRAG to extract entities and relationships. This option consumes fewer tokens, less memory, and fewer computational resources.</br>
General: Use prompts provided by github.com/microsoft/graphrag to extract entities and relationships`,
resolution: 'Entity resolution',
resolutionTip: `The resolution procedure would merge entities with the same meaning together which allows the graph conciser and more accurate. Entities as following should be merged: President Trump, Donald Trump, Donald J. Trump, Donald John Trump`,
resolutionTip: `An entity deduplication switch. When enabled, the LLM will combine similar entities - e.g., '2025' and 'the year of 2025', or 'IT' and 'Information Technology' - to construct a more accurate graph`,
community: 'Community reports generation',
communityTip:
'Chunks are clustered into hierarchical communities with entities and relationships connecting each segment up through higher levels of abstraction. We then use an LLM to generate a summary of each community, known as a community report. More: https://www.microsoft.com/en-us/research/blog/graphrag-improving-global-search-via-dynamic-community-selection/',
'In a knowledge graph, a community is a cluster of entities linked by relationships. You can have the LLM generate an abstract for each community, known as a community report. See here for more information: https://www.microsoft.com/en-us/research/blog/graphrag-improving-global-search-via-dynamic-community-selection/',
},
chunk: {
chunk: 'Chunk',