docs: add release notes for 0.4.0 (#554)

also fix #557
pingcap · Jan 3, 2025 · e605652 · e605652
1 parent 812224f
commit e605652
Show file tree

Hide file tree

Showing 9 changed files with 133 additions and 55 deletions.
diff --git a/frontend/app/src/pages/docs/embedding-model.mdx b/frontend/app/src/pages/docs/embedding-model.mdx
@@ -46,7 +46,7 @@ To use OpenAI-Like embedding model providers, you need to provide the **base URL
 }
 ```
 
-#### ZhipuAI
+#### ZhipuAI BigModel
 
 For example, the embedding API endpoint for ZhipuAI is:
 

diff --git a/frontend/app/src/pages/docs/evaluation.mdx b/frontend/app/src/pages/docs/evaluation.mdx
@@ -1,4 +1,4 @@
-# Evaluation
+# Evaluation (beta)
 
 The **Evaluation** module is an integral part of the Chat Engine of the AutoFlow, designed to assess the performance and reliability of the Chat Engine's outputs.
 

diff --git a/frontend/app/src/pages/docs/llm.mdx b/frontend/app/src/pages/docs/llm.mdx
@@ -26,53 +26,105 @@ If you want to use the new LLM while answering user queries, you need switch to
 
 Currently Autoflow supports the following LLM providers:
 
-- [OpenAI](https://platform.openai.com/)
-- [Google Gemini](https://gemini.google.com/)
-- [Anthropic Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude)
-- [Amazon Bedrock](https://aws.amazon.com/bedrock/)
-    - To use Amazon Bedrock, you'll need to provide a JSON Object of your AWS Credentials, as described in the [AWS CLI config global settings](https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-files.html#cli-configure-files-global):
-    ```json
-    {
-        "aws_access_key_id": "****",
-        "aws_secret_access_key": "****",
-        "aws_region_name": "us-west-2"
-    }
-    ```
-- [Gitee AI](https://ai.gitee.com/serverless-api)
-- And all OpenAI-Like models:
-    - [OpenRouter](https://openrouter.ai/)
-        - Default config:
-        ```json
-        {
-            "api_base": "https://openrouter.ai/api/v1/"
-        }
-        ```
-    - [BigModel](https://open.bigmodel.cn/)
-        - Default config:
-        ```json
-        {
-            "api_base": "https://open.bigmodel.cn/api/paas/v4/",
-            "is_chat_model": true
-        }
-        ```
-    - [Ollama](https://ollama.com/)
-        - Default config:
-        ```json
-        {
-            "api_base": "http://localhost:11434"
-        }
-        ```
-    - [vLLM](https://docs.vllm.ai/en/stable/)
-        - Default config:
-        ```json
-        {
-            "api_base": "http://localhost:8000/v1/"
-        }
-        ```
-    - [Xinference](https://inference.readthedocs.io/en/latest/index.html)
-        - Default config:
-        ```json
-        {
-            "api_base": "http://localhost:9997/v1/"
-        }
-        ```
+### OpenAI
+
+To learn more about OpenAI, please visit [OpenAI](https://platform.openai.com/).
+
+### Google Gemini
+
+To learn more about Google Gemini, please visit [Google Gemini](https://gemini.google.com/).
+
+### Anthropic Vertex AI
+
+To learn more about Anthropic Vertex AI, please visit [Anthropic Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude)
+
+### Amazon Bedrock
+
+To use Amazon Bedrock, you'll need to provide a JSON Object of your AWS Credentials, as described in the [AWS CLI config global settings](https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-files.html#cli-configure-files-global):
+
+```json
+{
+    "aws_access_key_id": "****",
+    "aws_secret_access_key": "****",
+    "aws_region_name": "us-west-2"
+}
+```
+
+To learn more about Amazon Bedrock, please visit [Amazon Bedrock](https://aws.amazon.com/bedrock/).
+
+### Gitee AI
+
+To learn more about Gitee AI, please visit [Gitee AI](https://ai.gitee.com/serverless-api).
+
+### OpenAI-Like
+
+Autoflow also support the providers that conform to the OpenAI API specification.
+
+To use OpenAI-Like LLM providers, you need to provide the **api_base** of the LLM API as the following JSON format in **Advanced Settings**:
+
+```json
+{
+    "api_base": "{api_base_url}"
+}
+```
+
+#### OpenRouter
+
+Default config:
+
+```json
+{
+   "api_base": "https://openrouter.ai/api/v1/"
+}
+```
+
+To learn more about OpenRouter, please visit [OpenRouter](https://openrouter.ai/).
+
+#### ZhipuAI BigModel
+
+Default config:
+
+```json
+{
+    "api_base": "https://open.bigmodel.cn/api/paas/v4/",
+    "is_chat_model": true
+}
+```
+
+To learn more about BigModel, please visit [BigModel](https://open.bigmodel.cn/).
+
+#### Ollama
+
+Default config:
+
+```json
+{
+    "api_base": "http://localhost:11434"
+}
+```
+
+To learn more about Ollama, please visit [Ollama](https://ollama.com/).
+
+#### vLLM
+
+Default config:
+
+```json
+{
+    "api_base": "http://localhost:8000/v1/"
+}
+```
+
+To learn more about vLLM, please visit [vLLM](https://docs.vllm.ai/en/stable/).
+
+#### Xinference
+
+Default config:
+
+```json
+{
+    "api_base": "http://localhost:9997/v1/"
+}
+```
+
+To learn more about Xinference, please visit [Xinference](https://inference.readthedocs.io/en/latest/).
diff --git a/frontend/app/src/pages/docs/releases b/frontend/app/src/pages/docs/releases
diff --git a/releases/_meta.ts → ...tend/app/src/pages/docs/releases/_meta.ts b/releases/_meta.ts → ...tend/app/src/pages/docs/releases/_meta.ts
diff --git a/releases/v0.1.0.md → ...end/app/src/pages/docs/releases/v0.1.0.md b/releases/v0.1.0.md → ...end/app/src/pages/docs/releases/v0.1.0.md
diff --git a/releases/v0.2.0.md → ...end/app/src/pages/docs/releases/v0.2.0.md b/releases/v0.2.0.md → ...end/app/src/pages/docs/releases/v0.2.0.md
diff --git a/releases/v0.3.0.md → ...end/app/src/pages/docs/releases/v0.3.0.md b/releases/v0.3.0.md → ...end/app/src/pages/docs/releases/v0.3.0.md
@@ -4,10 +4,14 @@
 
 - Rename project to `autoflow`
 - Multiple Knowledge Bases support
+- Support new LLM providers
+  - [OpenRouter](../llm.mdx#openrouter)
+  - [ZhipuAI BigModel](../llm.mdx#zhipuai-bigmodel)
+  - [Ollama](../llm.mdx#ollama)
 - Support new embedding models providers
   - [Ollama](../embedding-model.mdx#ollama)
-  - [OpenAI Like](../embedding-model.mdx#openai-like)
-  - [ZhipuAI](../embedding-model.mdx#zhipuai)
+  - Support [OpenAI Like](../embedding-model.mdx#openai-like) embedding model providers
+    - [ZhipuAI BigModel](../embedding-model.mdx#zhipuai-bigmodel)
 
 ## Breaking Changes
 

diff --git a/frontend/app/src/pages/docs/releases/v0.4.0.md b/frontend/app/src/pages/docs/releases/v0.4.0.md
@@ -0,0 +1,23 @@
+# Release Notes for v0.4.0 (release candidate)
+
+## Highlights
+
+- Support [Evaluation (beta)](../evaluation.mdx) tool to evaluate the performance and reliability of the Chat Engine’s outputs.
+  - Current support key metrics:
+    - Factual Correctness
+    - Semantic Similarity
+- Support new LLM providers
+  - [Gitee AI](../llm.mdx#gitee-ai)
+  - Test new OpenAI-like providers
+    - [vLLM](../llm.mdx#vllm)
+    - [Xinference](../llm.mdx#xinference)
+- Support new embedding model providers
+  - [Gitee AI](../embedding-model.mdx#gitee-ai)
+  - [Amazon Bedrock](../embedding-model.mdx#amazon-bedrock)
+
+## Improvements
+
+- Limit the upload file size via `max_upload_file_size` (10MB by default) parameter on site setting
+- Support download the reference file in the chat page
+
+If you are deploying Autoflow using docker, please follow the [Upgrade](../deploy-with-docker.mdx#upgrade) guide to upgrade your Autoflow.
-Original file line number
+Diff line change
@@ Expand Up @@
     }
     ```
-    #### ZhipuAI
+    #### ZhipuAI BigModel
     For example, the embedding API endpoint for ZhipuAI is:
@@ Expand Down @@