Merge remote-tracking branch 'origin/main' into ghrc

hellofinch · Dec 30, 2024 · 87374a6 · 87374a6
2 parents fcc5bdf + ba7b3f2
commit 87374a6
Show file tree

Hide file tree

Showing 17 changed files with 829 additions and 281 deletions.
diff --git a/.github/workflows/python-build.yml b/.github/workflows/python-build.yml
@@ -2,8 +2,6 @@ name: Test and Build Python Package
 
 on:
   push:
-    branches:
-      - main
   pull_request:
 
 jobs:

diff --git a/README.md b/README.md
@@ -41,8 +41,11 @@ PDF scientific paper translation and bilingual comparison.
 
 Feel free to provide feedback in [GitHub Issues](https://github.com/Byaidu/PDFMathTranslate/issues), [Telegram Group](https://t.me/+Z9_SgnxmsmA5NzBl) or [QQ Group](https://qm.qq.com/q/DixZCxQej0).
 
+For details on how to contribute, please consult the [Contribution Guide](https://github.com/Byaidu/PDFMathTranslate/wiki/Contribution-Guide---%E8%B4%A1%E7%8C%AE%E6%8C%87%E5%8D%97).
+
 <h2 id="updates">Updates</h2>
 
+- [Dec. 24 2024] The translator now supports local models on [Xinference](https://github.com/xorbitsai/inference) _(by [@imClumsyPanda](https://github.com/imClumsyPanda))_
 - [Dec. 19 2024] Non-PDF/A documents are now supported using `-cp` _(by [@reycn](https://github.com/reycn))_
 - [Dec. 13 2024] Additional support for backend by _(by [@YadominJinta](https://github.com/YadominJinta))_
 - [Dec. 10 2024] The translator now supports OpenAI models on Azure _(by [@yidasanqian](https://github.com/yidasanqian))_

diff --git a/docs/ADVANCED.md b/docs/ADVANCED.md
@@ -48,12 +48,13 @@ pdf2zh example.pdf -li en -lo ja
 We've provided a detailed table on the required [environment variables](https://chatgpt.com/share/6734a83d-9d48-800e-8a46-f57ca6e8bcb4) for each translation service. Make sure to set them before using the respective service.
 
 | **Translator**       | **Service**    | **Environment Variables**                                             | **Default Values**                                       | **Notes**                                                                                                                                                                                                 |
-| -------------------- | -------------- | --------------------------------------------------------------------- | -------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+|----------------------|----------------|-----------------------------------------------------------------------|----------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | **Google (Default)** | `google`       | None                                                                  | N/A                                                      | None                                                                                                                                                                                                      |
 | **Bing**             | `bing`         | None                                                                  | N/A                                                      | None                                                                                                                                                                                                      |
 | **DeepL**            | `deepl`        | `DEEPL_AUTH_KEY`                                                      | `[Your Key]`                                             | See [DeepL](https://support.deepl.com/hc/en-us/articles/360020695820-API-Key-for-DeepL-s-API)                                                                                                             |
 | **DeepLX**           | `deeplx`       | `DEEPLX_ENDPOINT`                                                     | `https://api.deepl.com/translate`                        | See [DeepLX](https://github.com/OwO-Network/DeepLX)                                                                                                                                                       |
 | **Ollama**           | `ollama`       | `OLLAMA_HOST`, `OLLAMA_MODEL`                                         | `http://127.0.0.1:11434`, `gemma2`                       | See [Ollama](https://github.com/ollama/ollama)                                                                                                                                                            |
+| **Xinference**       | `xinference`   | `XINFERENCE_HOST`, `XINFERENCE_MODEL`                                 | `http://127.0.0.1:9997`, `gemma-2-it`                    | See [Xinference](https://github.com/xorbitsai/inference)                                                                                                                                                                                        |
 | **OpenAI**           | `openai`       | `OPENAI_BASE_URL`, `OPENAI_API_KEY`, `OPENAI_MODEL`                   | `https://api.openai.com/v1`, `[Your Key]`, `gpt-4o-mini` | See [OpenAI](https://platform.openai.com/docs/overview)                                                                                                                                                   |
 | **AzureOpenAI**      | `azure-openai` | `AZURE_OPENAI_BASE_URL`, `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_MODEL` | `[Your Endpoint]`, `[Your Key]`, `gpt-4o-mini`           | See [Azure OpenAI](https://learn.microsoft.com/zh-cn/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line%2Cjavascript-keyless%2Ctypescript-keyless%2Cpython&pivots=programming-language-python) |
 | **Zhipu**            | `zhipu`        | `ZHIPU_API_KEY`, `ZHIPU_MODEL`                                        | `[Your Key]`, `glm-4-flash`                              | See [Zhipu](https://open.bigmodel.cn/dev/api/thirdparty-frame/openai-sdk)                                                                                                                                 |
@@ -64,7 +65,12 @@ We've provided a detailed table on the required [environment variables](https://
 | **Tencent**          | `tencent`      | `TENCENTCLOUD_SECRET_ID`, `TENCENTCLOUD_SECRET_KEY`                   | `[Your ID]`, `[Your Key]`                                | See [Tencent](https://www.tencentcloud.com/products/tmt?from_qcintl=122110104)                                                                                                                            |
 | **Dify**             | `dify`         | `DIFY_API_URL`, `DIFY_API_KEY`                                        | `[Your DIFY URL]`, `[Your Key]`                          | See [Dify](https://github.com/langgenius/dify),Three variables, lang_out, lang_in, and text, need to be defined in Dify's workflow input.                                                                 |
 | **AnythingLLM**      | `anythingllm`  | `AnythingLLM_URL`, `AnythingLLM_APIKEY`                               | `[Your AnythingLLM URL]`, `[Your Key]`                   | See [anything-llm](https://github.com/Mintplex-Labs/anything-llm)                                                                                                                                         |
-|**Argos Translate**|`argos-translate`| | |See [argos-translate](https://github.com/argosopentech/argos-translate)|
+|**Argos Translate**|`argos`| | |See [argos-translate](https://github.com/argosopentech/argos-translate)|
+|**Grok**|`grok`| `GORK_API_KEY`, `GORK_MODEL` | `[Your GORK_API_KEY]`, `grok-2-1212` |See [Grok](https://docs.x.ai/docs/overview)|
+|**DeepSeek**|`deepseek`| `DEEPSEEK_API_KEY`, `DEEPSEEK_MODEL` | `[Your DEEPSEEK_API_KEY]`, `deepseek-chat` |See [DeepSeek](https://www.deepseek.com/)|
+|**OpenAI-Liked**|`openai-liked`| `OPENAILIKE_BASE_URL`, `OPENAILIKE_API_KEY`, `OPENAILIKE_MODEL` | `url`, `[Your Key]`, `model name` | None |
+
+For large language models that are compatible with the OpenAI API but not listed in the table above, you can set environment variables using the same method outlined for OpenAI in the table.
 
 Use `-s service` or `-s service:model` to specify service:
 
@@ -94,7 +100,7 @@ pdf2zh example.pdf -f "(CM[^RT].*|MS.*|.*Ital)" -c "(\(|\||\)|\+|=|\d|[\u0080-\u
 Preserve `Latex`, `Mono`, `Code`, `Italic`, `Symbol` and `Math` fonts by default:
 
 ```bash
-pdf2zh example.pdf -f "(CM[^R]|(MS|XY|MT|BL|RM|EU|LA|RS)[A-Z]|LINE|LCIRCLE|TeX-|rsfs|txsy|wasy|stmary|.*Mono|.*Code|.*Ital|.*Sym|.*Math)"
+pdf2zh example.pdf -f "(CM[^R]|MS.M|XY|MT|BL|RM|EU|LA|RS|LINE|LCIRCLE|TeX-|rsfs|txsy|wasy|stmary|.*Mono|.*Code|.*Ital|.*Sym|.*Math)"
 ```
 
 [⬆️ Back to top](#toc)
@@ -168,7 +174,7 @@ test,test123
 
 example auth.html
 
-```
+```html
 <!DOCTYPE html>
 <html>
 <head>

diff --git a/docs/APIS.md b/docs/APIS.md
@@ -1,7 +1,7 @@
 [**Documentation**](https://github.com/Byaidu/PDFMathTranslate) > **API Details** _(current)_
 
 <h2 id="toc">Table of Content</h2>
-The present project supports two types of APIs;
+The present project supports two types of APIs, All methods need the Redis;
 
 - [Functional calls in Python](#api-python)
 - [HTTP protocols](#api-http)

diff --git a/docs/README_ja-JP.md b/docs/README_ja-JP.md
@@ -2,7 +2,7 @@
 
 [English](../README.md) | [简体中文](README_zh-CN.md) | 日本語
 
-<img src="./docs/images/banner.png" width="320px"  alt="PDF2ZH"/>  
+<img src="./images/banner.png" width="320px"  alt="PDF2ZH"/>  
 
 <h2 id="title">PDFMathTranslate</h2>
 
@@ -56,7 +56,7 @@
 <h2 id="preview">プレビュー</h2>
 
 <div align="center">
-<img src="./docs/images/preview.gif" width="80%"/>
+<img src="./images/preview.gif" width="80%"/>
 </div>
 
 <h2 id="demo">公共サービス 🌟</h2>
@@ -122,9 +122,9 @@ Python環境を事前にインストールする必要はありません
     http://localhost:7860/
     ```
 
-    <img src="./docs/images/gui.gif" width="500"/>
+    <img src="./images/gui.gif" width="500"/>
 
-詳細については、[GUIのドキュメント](./docs/README_GUI.md) を参照してください。
+詳細については、[GUIのドキュメント](./README_GUI.md) を参照してください。
 
 <h3 id="docker">方法4. Docker</h3>
 
@@ -158,7 +158,7 @@ Python環境を事前にインストールする必要はありません
 
 コマンドラインで翻訳コマンドを実行し、現在の作業ディレクトリに翻訳されたドキュメント `example-mono.pdf` とバイリンガルドキュメント `example-dual.pdf` を生成します。デフォルトではGoogle翻訳サービスを使用します。
 
-<img src="./docs/images/cmd.explained.png" width="580px"  alt="cmd"/>  
+<img src="./images/cmd.explained.png" width="580px"  alt="cmd"/>  
 
 以下の表に、参考のためにすべての高度なオプションをリストしました：
 
@@ -223,7 +223,13 @@ pdf2zh example.pdf -li en -lo ja
 |**Tencent**|`tencent`|`TENCENTCLOUD_SECRET_ID`, `TENCENTCLOUD_SECRET_KEY`|`[Your ID]`, `[Your Key]`|See [Tencent](https://www.tencentcloud.com/products/tmt?from_qcintl=122110104)|
 |**Dify**|`dify`|`DIFY_API_URL`, `DIFY_API_KEY`|`[Your DIFY URL]`, `[Your Key]`|See [Dify](https://github.com/langgenius/dify),Three variables, lang_out, lang_in, and text, need to be defined in Dify's workflow input.|
 |**AnythingLLM**|`anythingllm`|`AnythingLLM_URL`, `AnythingLLM_APIKEY`|`[Your AnythingLLM URL]`, `[Your Key]`|See [anything-llm](https://github.com/Mintplex-Labs/anything-llm)|
-|**Argos Translate**|`argos-translate`| | |See [argos-translate](https://github.com/argosopentech/argos-translate)|
+|**Argos Translate**|`argos`| | |See [argos-translate](https://github.com/argosopentech/argos-translate)|
+|**Grok**|`grok`| `GORK_API_KEY`, `GORK_MODEL` | `[Your GORK_API_KEY]`, `grok-2-1212` |See [Grok](https://docs.x.ai/docs/overview)|
+|**DeepSeek**|`deepseek`| `DEEPSEEK_API_KEY`, `DEEPSEEK_MODEL` | `[Your DEEPSEEK_API_KEY]`, `deepseek-chat` |See [DeepSeek](https://www.deepseek.com/)|
+|**OpenAI-Liked**|`openai-liked`| `OPENAILIKE_BASE_URL`, `OPENAILIKE_API_KEY`, `OPENAILIKE_MODEL` | `url`, `[Your Key]`, `model name` | None |
+
+(need Japenese translation)
+For large language models that are compatible with the OpenAI API but not listed in the table above, you can set environment variables using the same method outlined for OpenAI in the table.
 
 `-s service` または `-s service:model` を使用してサービスを指定します：
 
@@ -249,7 +255,7 @@ pdf2zh example.pdf -f "(CM[^RT].*|MS.*|.*Ital)" -c "(\(|\||\)|\+|=|\d|[\u0080-\u
 デフォルトで `Latex`、`Mono`、`Code`、`Italic`、`Symbol` および `Math` フォントを保持します：
 
 ```bash
-pdf2zh example.pdf -f "(CM[^R]|(MS|XY|MT|BL|RM|EU|LA|RS)[A-Z]|LINE|LCIRCLE|TeX-|rsfs|txsy|wasy|stmary|.*Mono|.*Code|.*Ital|.*Sym|.*Math)"
+pdf2zh example.pdf -f "(CM[^R]|MS.M|XY|MT|BL|RM|EU|LA|RS|LINE|LCIRCLE|TeX-|rsfs|txsy|wasy|stmary|.*Mono|.*Code|.*Ital|.*Sym|.*Math)"
 ```
 
 <h3 id="threads">スレッド数を指定</h3>
@@ -260,16 +266,18 @@ pdf2zh example.pdf -f "(CM[^R]|(MS|XY|MT|BL|RM|EU|LA|RS)[A-Z]|LINE|LCIRCLE|TeX-|
 pdf2zh example.pdf -t 1
 ```
 
-<h3 id="prompt">custom prompt</h3>
-(need Japenese translation)
-Use `--prompt` to specify which prompt to use in llm:
+<h3 id="prompt">カスタム プロンプト</h3>
+
+`--prompt`を使用して、LLMで使用するプロンプトを指定します：
+
 ```bash
 pdf2zh example.pdf -pr prompt.txt
 ```
 
 
-example prompt.txt
-```
+`prompt.txt`の例：
+
+```txt
 [
     {
         "role": "system",
@@ -283,12 +291,14 @@ example prompt.txt
 ```
 
 
-In custom prompt file, there are three variables can be used.
-|**variables**|**comment**|
+カスタムプロンプトファイルでは、以下の3つの変数が使用できます。
+
+|**変数**|**内容**|
 |-|-|
-|`lang_in`|input language|
-|`lang_out`|output language|
-|`text`|text need to be translated|
+|`lang_in`|ソース言語|
+|`lang_out`|ターゲット言語|
+|`text`|翻訳するテキスト|
+
 <h2 id="todo">API</h2>
 
 ### Python

diff --git a/docs/README_zh-CN.md b/docs/README_zh-CN.md
@@ -2,7 +2,7 @@
 
 [English](../README.md) | 简体中文 | [日本語](README_ja-JP.md)
 
-<img src="./docs/images/banner.png" width="320px"  alt="PDF2ZH"/>  
+<img src="./images/banner.png" width="320px"  alt="PDF2ZH"/>  
 
 <h2 id="title">PDFMathTranslate</h2>
 
@@ -41,8 +41,11 @@
 
 欢迎在 [GitHub Issues](https://github.com/Byaidu/PDFMathTranslate/issues)、[Telegram 用户群](https://t.me/+Z9_SgnxmsmA5NzBl) 或 [QQ 用户群](https://qm.qq.com/q/DixZCxQej0) 中提供反馈
 
+有关如何贡献的详细信息，请查阅 [贡献指南](https://github.com/Byaidu/PDFMathTranslate/wiki/Contribution-Guide---%E8%B4%A1%E7%8C%AE%E6%8C%87%E5%8D%97)
+
 <h2 id="updates">近期更新</h2>
 
+- [Dec. 24 2024] 翻译功能支持接入 [Xinference](https://github.com/xorbitsai/inference) 运行的本地 LLM _(by [@imClumsyPanda](https://github.com/imClumsyPanda))_
 - [Nov. 26 2024] CLI 现在已支持（多个）在线 PDF 文件 *(by [@reycn](https://github.com/reycn))*  
 - [Nov. 24 2024] 为降低依赖大小，提供 [ONNX](https://github.com/onnx/onnx) 支持 *(by [@Wybxc](https://github.com/Wybxc))*  
 - [Nov. 23 2024] 🌟 [免费公共服务](#demo) 上线! *(by [@Byaidu](https://github.com/Byaidu))*  
@@ -56,7 +59,7 @@
 <h2 id="preview">效果预览</h2>
 
 <div align="center">
-<img src="./docs/images/preview.gif" width="80%"/>
+<img src="./images/preview.gif" width="80%"/>
 </div>
 
 <h2 id="demo">在线演示 🌟</h2>
@@ -121,9 +124,9 @@ set HF_ENDPOINT=https://hf-mirror.com
     http://localhost:7860/
     ```
 
-    <img src="./docs/images/gui.gif" width="500"/>
+    <img src="./images/gui.gif" width="500"/>
 
-查看 [documentation for GUI](./docs/README_GUI.md) 获取细节说明
+查看 [documentation for GUI](/README_GUI.md) 获取细节说明
 
 <h3 id="docker">方法四、容器化部署</h3>
 
@@ -157,7 +160,7 @@ set HF_ENDPOINT=https://hf-mirror.com
 
 在命令行中执行翻译命令，在当前工作目录下生成译文文档 `example-mono.pdf` 和双语对照文档 `example-dual.pdf`，默认使用 Google 翻译服务
 
-<img src="./docs/images/cmd.explained.png" width="580px"  alt="cmd"/>  
+<img src="./images/cmd.explained.png" width="580px"  alt="cmd"/>  
 
 我们在下表中列出了所有高级选项，以供参考：
 
@@ -222,7 +225,12 @@ pdf2zh example.pdf -li en -lo ja
 |**Tencent**|`tencent`|`TENCENTCLOUD_SECRET_ID`, `TENCENTCLOUD_SECRET_KEY`|`[Your ID]`, `[Your Key]`|See [Tencent](https://www.tencentcloud.com/products/tmt?from_qcintl=122110104)|
 |**Dify**|`dify`|`DIFY_API_URL`, `DIFY_API_KEY`|`[Your DIFY URL]`, `[Your Key]`|See [Dify](https://github.com/langgenius/dify),Three variables, lang_out, lang_in, and text, need to be defined in Dify's workflow input.|
 |**AnythingLLM**|`anythingllm`|`AnythingLLM_URL`, `AnythingLLM_APIKEY`|`[Your AnythingLLM URL]`, `[Your Key]`|See [anything-llm](https://github.com/Mintplex-Labs/anything-llm)|
-|**Argos Translate**|`argos-translate`| | |See [argos-translate](https://github.com/argosopentech/argos-translate)|
+|**Argos Translate**|`argos`| | |See [argos-translate](https://github.com/argosopentech/argos-translate)|
+|**Grok**|`grok`| `GORK_API_KEY`, `GORK_MODEL` | `[Your GORK_API_KEY]`, `grok-2-1212` |See [Grok](https://docs.x.ai/docs/overview)|
+|**DeepSeek**|`deepseek`| `DEEPSEEK_API_KEY`, `DEEPSEEK_MODEL` | `[Your DEEPSEEK_API_KEY]`, `deepseek-chat` |See [DeepSeek](https://www.deepseek.com/)|
+|**OpenAI-Liked**|`openai-liked`| `OPENAILIKE_BASE_URL`, `OPENAILIKE_API_KEY`, `OPENAILIKE_MODEL` | `url`, `[Your Key]`, `model name` | None |
+
+对于未在上述表格中的，并且兼容 OpenAI api 的大语言模型，可使用表格中的 OpenAI 的方式进行环境变量的设置。
 
 使用 `-s service` 或 `-s service:model` 指定翻译服务:
 
@@ -248,7 +256,7 @@ pdf2zh example.pdf -f "(CM[^RT].*|MS.*|.*Ital)" -c "(\(|\||\)|\+|=|\d|[\u0080-\u
 默认保留 `Latex`, `Mono`, `Code`, `Italic`, `Symbol` 以及 `Math` 字体：
 
 ```bash
-pdf2zh example.pdf -f "(CM[^R]|(MS|XY|MT|BL|RM|EU|LA|RS)[A-Z]|LINE|LCIRCLE|TeX-|rsfs|txsy|wasy|stmary|.*Mono|.*Code|.*Ital|.*Sym|.*Math)"
+pdf2zh example.pdf -f "(CM[^R]|MS.M|XY|MT|BL|RM|EU|LA|RS|LINE|LCIRCLE|TeX-|rsfs|txsy|wasy|stmary|.*Mono|.*Code|.*Ital|.*Sym|.*Math)"
 ```
 
 <h3 id="threads">指定线程数量</h3>

diff --git a/pdf2zh/backend.py b/pdf2zh/backend.py
@@ -6,6 +6,7 @@
 import tqdm
 import json
 import io
+from pdf2zh.pdf2zh import model
 
 flask_app = Flask("pdf2zh")
 flask_app.config.from_mapping(
@@ -47,6 +48,7 @@ def progress_bar(t: tqdm.tqdm):
     doc_mono, doc_dual = translate_stream(
         stream,
         callback=progress_bar,
+        model=model,
         **args,
     )
     return doc_mono, doc_dual
-Original file line number
+Diff line change
@@ Expand Up / @@ -2,8 +2,6 @@ name: Test and Build Python Package @@
     on:
       push:
-        branches:
-          - main
       pull_request:
     jobs:
@@ Expand Down @@