From 6e42687e658fe77e386b1fb249d880bc44f74998 Mon Sep 17 00:00:00 2001 From: writinwaters <93570324+writinwaters@users.noreply.github.com> Date: Mon, 10 Feb 2025 17:05:24 +0800 Subject: [PATCH] Added a release notes (#4848) ### What problem does this PR solve? ### Type of change - [x] Documentation Update --- docs/guides/start_chat.md | 2 +- .../agent_component_reference/categorize.mdx | 8 ++--- .../agent_component_reference/generate.mdx | 4 +-- .../agent_component_reference/keyword.mdx | 4 +-- .../agent_component_reference/rewrite.mdx | 4 +-- docs/release_notes.md | 36 +++++++++++++++++++ web/src/locales/en.ts | 2 +- 7 files changed, 48 insertions(+), 12 deletions(-) diff --git a/docs/guides/start_chat.md b/docs/guides/start_chat.md index 7bc234cde..89b7b35bc 100644 --- a/docs/guides/start_chat.md +++ b/docs/guides/start_chat.md @@ -46,7 +46,7 @@ You start an AI conversation by creating an assistant. 4. Update **Model Setting**: - In **Model**: you select the chat model. Though you have selected the default chat model in **System Model Settings**, RAGFlow allows you to choose an alternative chat model for your dialogue. - - **Freedom** refers to the level that the LLM improvises. From **Improvise**, **Precise**, to **Balance**, each freedom level corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**. + - **Preset configurations** refers to the level that the LLM improvises. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**. - **Temperature**: Level of the prediction randomness of the LLM. The higher the value, the more creative the LLM is. - **Top P** is also known as "nucleus sampling". See [here](https://en.wikipedia.org/wiki/Top-p_sampling) for more information. - **Max Tokens**: The maximum length of the LLM's responses. Note that the responses may be curtailed if this value is set too low. diff --git a/docs/references/agent_component_reference/categorize.mdx b/docs/references/agent_component_reference/categorize.mdx index 4134dd765..a034e4622 100644 --- a/docs/references/agent_component_reference/categorize.mdx +++ b/docs/references/agent_component_reference/categorize.mdx @@ -33,13 +33,13 @@ Click the dropdown menu of **Model** to show the model configuration window. - **Model**: The chat model to use. - Ensure you set the chat model correctly on the **Model providers** page. - You can use different models for different components to increase flexibility or improve overall performance. -- **Freedom**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. - This parameter has three options: +- **Preset configurations**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**. + This parameter has three options: - **Improvise**: Produces more creative responses. - **Precise**: (Default) Produces more conservative responses. - **Balance**: A middle ground between **Improvise** and **Precise**. - **Temperature**: The randomness level of the model's output. - Defaults to 0.1. + Defaults to 0.1. - Lower values lead to more deterministic and predictable outputs. - Higher values lead to more creative and varied outputs. - A temperature of zero results in the same output for the same prompt. @@ -58,7 +58,7 @@ Click the dropdown menu of **Model** to show the model configuration window. :::tip NOTE - It is not necessary to stick with the same model for all components. If a specific model is not performing well for a particular task, consider using a different one. -- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, you can simply choose one of the three options of **Freedom**. +- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, simply choose one of the three options of **Preset configurations**. ::: ### Message window size diff --git a/docs/references/agent_component_reference/generate.mdx b/docs/references/agent_component_reference/generate.mdx index 6572bc35a..7656b00a2 100644 --- a/docs/references/agent_component_reference/generate.mdx +++ b/docs/references/agent_component_reference/generate.mdx @@ -24,7 +24,7 @@ Click the dropdown menu of **Model** to show the model configuration window. - **Model**: The chat model to use. - Ensure you set the chat model correctly on the **Model providers** page. - You can use different models for different components to increase flexibility or improve overall performance. -- **Freedom**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. +- **Preset configurations**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**. This parameter has three options: - **Improvise**: Produces more creative responses. - **Precise**: (Default) Produces more conservative responses. @@ -49,7 +49,7 @@ Click the dropdown menu of **Model** to show the model configuration window. :::tip NOTE - It is not necessary to stick with the same model for all components. If a specific model is not performing well for a particular task, consider using a different one. -- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, you can simply choose one of the three options of **Freedom**. +- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, simply choose one of the three options of **Preset configurations**. ::: ### System prompt diff --git a/docs/references/agent_component_reference/keyword.mdx b/docs/references/agent_component_reference/keyword.mdx index 5d26c453f..0b0c55504 100644 --- a/docs/references/agent_component_reference/keyword.mdx +++ b/docs/references/agent_component_reference/keyword.mdx @@ -34,7 +34,7 @@ Click the dropdown menu of **Model** to show the model configuration window. - **Model**: The chat model to use. - Ensure you set the chat model correctly on the **Model providers** page. - You can use different models for different components to increase flexibility or improve overall performance. -- **Freedom**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. +- **Preset configurations**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**. This parameter has three options: - **Improvise**: Produces more creative responses. - **Precise**: (Default) Produces more conservative responses. @@ -59,7 +59,7 @@ Click the dropdown menu of **Model** to show the model configuration window. :::tip NOTE - It is not necessary to stick with the same model for all components. If a specific model is not performing well for a particular task, consider using a different one. -- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, you can simply choose one of the three options of **Freedom**. +- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, simply choose one of the three options of **Preset**. ::: diff --git a/docs/references/agent_component_reference/rewrite.mdx b/docs/references/agent_component_reference/rewrite.mdx index cef3eaa45..27c9a8e03 100644 --- a/docs/references/agent_component_reference/rewrite.mdx +++ b/docs/references/agent_component_reference/rewrite.mdx @@ -32,7 +32,7 @@ Click the dropdown menu of **Model** to show the model configuration window. - **Model**: The chat model to use. - Ensure you set the chat model correctly on the **Model providers** page. - You can use different models for different components to increase flexibility or improve overall performance. -- **Freedom**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. +- **Preset configurations**: A shortcut to **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty** settings, indicating the freedom level of the model. From **Improvise**, **Precise**, to **Balance**, each preset configuration corresponds to a unique combination of **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**. This parameter has three options: - **Improvise**: Produces more creative responses. - **Precise**: (Default) Produces more conservative responses. @@ -57,7 +57,7 @@ Click the dropdown menu of **Model** to show the model configuration window. :::tip NOTE - It is not necessary to stick with the same model for all components. If a specific model is not performing well for a particular task, consider using a different one. -- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, you can simply choose one of the three options of **Freedom**. +- If you are uncertain about the mechanism behind **Temperature**, **Top P**, **Presence penalty**, and **Frequency penalty**, simply choose one of the three options of **Preset configurations**. ::: diff --git a/docs/release_notes.md b/docs/release_notes.md index f2f4d54de..10053547c 100644 --- a/docs/release_notes.md +++ b/docs/release_notes.md @@ -7,6 +7,42 @@ slug: /release_notes Key features, improvements and bug fixes in the latest releases. +## v0.16.0 + +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. +- 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. +- Upgrades RAGFlow's document engine [Infinity](https://github.com/infiniflow/infinity) to v0.6.0.dev3. +- Supports creating and referencing a **Tag** knowledge base as a key milestone towards bridging the semantic gap between query and response. + +:::danger IMPORTANT +The **Tag knowledge base** feature is *unavailable* on the [Infinity](https://github.com/infiniflow/infinity) document engine. +::: + +### Documentation + +#### Added documents + +- [Begin component](https://ragflow.io/docs/dev/begin_component) +- [Generate component](https://ragflow.io/docs/dev/generate_component) +- [Interact component](https://ragflow.io/docs/dev/interact_component) +- [Retrieval component](https://ragflow.io/docs/dev/retrieval_component) +- [Categorize component](https://ragflow.io/docs/dev/categorize_component) +- [Keyword component](https://ragflow.io/docs/dev/keyword_component) +- [Message component](https://ragflow.io/docs/dev/message_component) +- [Rewrite component](https://ragflow.io/docs/dev/rewrite_component) +- [Switch component](https://ragflow.io/docs/dev/switch_component) +- [Concentrator component](https://ragflow.io/docs/dev/concentrator_component) +- [Template component](https://ragflow.io/docs/dev/template_component) +- [Iteration component](https://ragflow.io/docs/dev/iteration_component) +- [Note component](https://ragflow.io/docs/dev/note_component) + ## v0.15.1 Released on December 25, 2024. diff --git a/web/src/locales/en.ts b/web/src/locales/en.ts index 442d1d2f6..494665d80 100644 --- a/web/src/locales/en.ts +++ b/web/src/locales/en.ts @@ -160,7 +160,7 @@ export default { rerankPlaceholder: 'Please select', rerankTip: `If left empty, RAGFlow will use a combination of weighted keyword similarity and weighted vector cosine similarity; if a rerank model is selected, a weighted reranking score will replace the weighted vector cosine similarity. Please be aware that using a rerank model will significantly increase the system's response time.`, topK: 'Top-K', - topKTip: `K chunks will be fed into rerank models.`, + topKTip: `K chunks will be sent into the rerank model.`, delimiter: `Delimiters`, delimiterTip: 'A delimiter or separator can consist of one or multiple special characters. If it is multiple characters, ensure they are enclosed in backticks( ``). For example, if you configure your delimiters like this: \n`##`;, then your texts will be separated at line breaks, double hash symbols (##), or semicolons.',