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

Updated outdated descriptions and added multi-turn optimization (#4362)

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
2025-01-06 16:54:22 +08:00
committed by GitHub
parent b93c136797
commit 45619702ff
7 changed files with 48 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
docs/guides/start_chat.md
View File

@ -5,6 +5,10 @@ slug: /start_chat
# Start an AI-powered chat
Initiate a chat with a configured chat assistant.
---
Knowledge base, hallucination-free chat, and file management are the three pillars of RAGFlow. Chats in RAGFlow are based on a particular knowledge base or multiple knowledge bases. Once you have created your knowledge base and finished file parsing, you can go ahead and start an AI conversation.
## Start an AI chat
@ -21,16 +25,23 @@ You start an AI conversation by creating an assistant.
- **Empty response**:
- If you wish to *confine* RAGFlow's answers to your knowledge bases, leave a response here. Then, when it doesn't retrieve an answer, it *uniformly* responds with what you set here.
- If you wish RAGFlow to *improvise* when it doesn't retrieve an answer from your knowledge bases, leave it blank, which may give rise to hallucinations.
- **Show quote**: This is a key feature of RAGFlow and enabled by default. RAGFlow does not work like a black box. instead, it clearly shows the sources of information that its responses are based on.
- **Show quote**: This is a key feature of RAGFlow and enabled by default. RAGFlow does not work like a black box. Instead, it clearly shows the sources of information that its responses are based on.
- Select the corresponding knowledge bases. You can select one or multiple knowledge bases, but ensure that they use the same embedding model, otherwise an error would occur.
3. Update **Prompt Engine**:
- In **System**, you fill in the prompts for your LLM, you can also leave the default prompt as-is for the beginning.
- **Similarity threshold** sets the similarity "bar" for each chunk of text. The default is 0.2. Text chunks with lower similarity scores are filtered out of the final response.
- **Vector similarity weight** is set to 0.3 by default. RAGFlow uses a hybrid score system, combining keyword similarity and vector similarity, for evaluating the relevance of different text chunks. This value sets the weight assigned to the vector similarity component in the hybrid score.
- **Keyword similarity weight** is set to 0.7 by default. RAGFlow uses a hybrid score system to evaluate the relevance of different text chunks. This value sets the weight assigned to the keyword similarity component in the hybrid score.
- If **Rerank model** is left empty, the hybrid score system uses keyword similarity and vector similarity, and the default weight assigned to the vector similarity component is 1-0.7=0.3.
- If **Rerank model** is selected, the hybrid score system uses keyword similarity and reranker score, and the default weight assigned to the reranker score is 1-0.7=0.3.
- **Top N** determines the *maximum* number of chunks to feed to the LLM. In other words, even if more chunks are retrieved, only the top N chunks are provided as input.
- **Variable**:
- **Multi-turn optimization** enhances user queries using existing context in a multi-round conversation. It is enabled by default. When enabled, it will consume additional LLM tokens and significantly increase the time to generate answers.
- **Rerank model** sets the reranker model to use. It is left empty by default.
- If **Rerank model** is left empty, the hybrid score system uses keyword similarity and vector similarity, and the default weight assigned to the vector similarity component is 1-0.7=0.3.
- If **Rerank model** is selected, the hybrid score system uses keyword similarity and reranker score, and the default weight assigned to the reranker score is 1-0.7=0.3.
- **Variable** refers to the variables (keys) to be used in the system prompt. `{knowledge}` is a reserved variable. Click **Add** to add more variables for the system prompt.
- If you are uncertain about the logic behind **Variable**, leave it *as-is*.
4. Update **Model Setting**:
@ -42,9 +53,18 @@ You start an AI conversation by creating an assistant.
5. Now, let's start the show:
![question1](https://github.com/infiniflow/ragflow/assets/93570324/bb72dd67-b35e-4b2a-87e9-4e4edbd6e677)
![question1](https://github.com/user-attachments/assets/c4114a3d-74ff-40a3-9719-6b47c7b11ab1)
![question2](https://github.com/infiniflow/ragflow/assets/93570324/7cc585ae-88d0-4aa2-817d-0370b2ad7230)
:::tip NOTE
Click the light bubble logo above the answer to view the expanded system prompt:
![](https://github.com/user-attachments/assets/515ab187-94e8-412a-82f2-aba52cd79e09)
Scroll down the expanded prompt to view the time consumed for each task:
![enlighten](https://github.com/user-attachments/assets/fedfa2ee-21a7-451b-be66-20125619923c)
:::
## Update settings of an existing chat assistant