Leon/docutranslate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

增加epub、html工作流的示例说明

Browse Source
This commit is contained in:
xunbu
2025-10-15 08:41:44 +08:00
parent e89c1174ed
commit d0fb9e4405
3 changed files with 277 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

241
README.md
View File

@@ -20,18 +20,26 @@
A lightweight local file translation tool based on Large Language Models A lightweight local file translation tool based on Large Language Models
</p> </p>
- ✅ **Multiple Format Support**: Translates various files including `pdf`, `docx`, `xlsx`, `md`, `txt`, `json`, `epub`, `srt`, `ass`, and more. - ✅ **Multiple Format Support**: Translates various files including `pdf`, `docx`, `xlsx`, `md`, `txt`, `json`, `epub`,
`srt`, `ass`, and more.
- ✅ **Automatic Glossary Generation**: Supports automatic generation of glossaries for term alignment. - ✅ **Automatic Glossary Generation**: Supports automatic generation of glossaries for term alignment.
- ✅ **PDF Table, Formula, and Code Recognition**: Recognizes and translates tables, formulas, and code often found in academic papers, powered by `docling` and `mineru` PDF parsing engines. - ✅ **PDF Table, Formula, and Code Recognition**: Recognizes and translates tables, formulas, and code often found in
- ✅ **JSON Translation**: Supports specifying values to be translated in JSON using JSON paths (following `jsonpath-ng` syntax). academic papers, powered by `docling` and `mineru` PDF parsing engines.
- ✅ **Word/Excel Format Preservation**: Translates `docx` and `xlsx` files while preserving their original formatting (does not yet support `doc` or `xls` files). - ✅ **JSON Translation**: Supports specifying values to be translated in JSON using JSON paths (following `jsonpath-ng`
- ✅ **Multi-AI Platform Support**: Compatible with most AI platforms, enabling high-performance, concurrent AI translation with custom prompts. syntax).
- ✅ **Asynchronous Support**: Designed for high-performance scenarios with full asynchronous support, offering service interfaces for parallel tasks. - ✅ **Word/Excel Format Preservation**: Translates `docx` and `xlsx` files while preserving their original formatting (
does not yet support `doc` or `xls` files).
- ✅ **Multi-AI Platform Support**: Compatible with most AI platforms, enabling high-performance, concurrent AI
translation with custom prompts.
- ✅ **Asynchronous Support**: Designed for high-performance scenarios with full asynchronous support, offering service
interfaces for parallel tasks.
- ✅ **LAN and Multi-user Support**: Can be used by multiple people simultaneously on a local area network. - ✅ **LAN and Multi-user Support**: Can be used by multiple people simultaneously on a local area network.
- ✅ **Interactive Web Interface**: Provides an out-of-the-box Web UI and RESTful API for easy integration and use. - ✅ **Interactive Web Interface**: Provides an out-of-the-box Web UI and RESTful API for easy integration and use.
- ✅ **Small, Multi-platform Standalone Packages**: Windows and Mac standalone packages under 40MB (for versions not using the `docling` local PDF parser). - ✅ **Small, Multi-platform Standalone Packages**: Windows and Mac standalone packages under 40MB (for versions not
using the `docling` local PDF parser).
> When translating `pdf` files, they are first converted to Markdown, which will **cause the original layout to be lost**. Users with strict layout requirements should take note. > When translating `pdf` files, they are first converted to Markdown, which will **cause the original layout to be lost
**. Users with strict layout requirements should take note.
> QQ Discussion Group: 1047781902 > QQ Discussion Group: 1047781902
@@ -46,10 +54,14 @@
## All-in-One Packages ## All-in-One Packages
For users who want to get started quickly, we provide all-in-one packages on [GitHub Releases](https://github.com/xunbu/docutranslate/releases). Simply download, unzip, and enter your AI platform API Key to begin. For users who want to get started quickly, we provide all-in-one packages
on [GitHub Releases](https://github.com/xunbu/docutranslate/releases). Simply download, unzip, and enter your AI
platform API Key to begin.
- **DocuTranslate**: Standard version, uses the online `minerU` engine to parse PDF documents. Choose this version if you don't need local PDF parsing (recommended). - **DocuTranslate**: Standard version, uses the online `minerU` engine to parse PDF documents. Choose this version if
- **DocuTranslate_full**: Full version, includes the built-in `docling` local PDF parsing engine. Choose this version if you need local PDF parsing. you don't need local PDF parsing (recommended).
- **DocuTranslate_full**: Full version, includes the built-in `docling` local PDF parsing engine. Choose this version if
you need local PDF parsing.
## Installation ## Installation
@@ -90,31 +102,35 @@ uv sync
## Core Concept: Workflow ## Core Concept: Workflow
The core of the new DocuTranslate is the **Workflow**. Each workflow is a complete, end-to-end translation pipeline designed for a specific file type. Instead of interacting with a single large class, you select and configure a workflow based on your file type. The core of the new DocuTranslate is the **Workflow**. Each workflow is a complete, end-to-end translation pipeline
designed for a specific file type. Instead of interacting with a single large class, you select and configure a workflow
based on your file type.
**The basic usage flow is as follows:** **The basic usage flow is as follows:**
1. **Select a Workflow**: Choose a workflow based on your input file type (e.g., PDF/Word or TXT), such as `MarkdownBasedWorkflow` or `TXTWorkflow`. 1. **Select a Workflow**: Choose a workflow based on your input file type (e.g., PDF/Word or TXT), such as
2. **Build Configuration**: Create the corresponding configuration object for the selected workflow (e.g., `MarkdownBasedWorkflowConfig`). This object contains all necessary sub-configurations, such as: `MarkdownBasedWorkflow` or `TXTWorkflow`.
* **Converter Config**: Defines how to convert the original file (like a PDF) to Markdown. 2. **Build Configuration**: Create the corresponding configuration object for the selected workflow (e.g.,
* **Translator Config**: Defines which LLM, API-Key, target language, etc., to use. `MarkdownBasedWorkflowConfig`). This object contains all necessary sub-configurations, such as:
* **Exporter Config**: Defines specific options for the output format (like HTML). * **Converter Config**: Defines how to convert the original file (like a PDF) to Markdown.
3. **Instantiate the Workflow**: Create an instance of the workflow using the configuration object. * **Translator Config**: Defines which LLM, API-Key, target language, etc., to use.
4. **Execute Translation**: Call the workflow's `.read_*()` and `.translate()` / `.translate_async()` methods. * **Exporter Config**: Defines specific options for the output format (like HTML).
5. **Export/Save Results**: Call the `.export_to_*()` or `.save_as_*()` methods to get or save the translation results. 3. **Instantiate the Workflow**: Create an instance of the workflow using the configuration object.
4. **Execute Translation**: Call the workflow's `.read_*()` and `.translate()` / `.translate_async()` methods.
5. **Export/Save Results**: Call the `.export_to_*()` or `.save_as_*()` methods to get or save the translation results.
## Available Workflows ## Available Workflows
| Workflow | Use Case | Input Formats | Output Formats | Core Config Class | | Workflow | Use Case | Input Formats | Output Formats | Core Config Class |
|:----------------------------|:----------------------------------------------------------------|:---------------------------------------------|:---------------------------|:------------------------------| |:----------------------------|:-------------------------------------------------------------------------------------------------------|:---------------------------------------------|:-----------------------|:------------------------------|
| **`MarkdownBasedWorkflow`** | Processes rich text documents like PDF, Word, images. Flow: `File -> Markdown -> Translate -> Export`. | `.pdf`, `.docx`, `.md`, `.png`, `.jpg`, etc. | `.md`, `.zip`, `.html` | `MarkdownBasedWorkflowConfig` | | **`MarkdownBasedWorkflow`** | Processes rich text documents like PDF, Word, images. Flow: `File -> Markdown -> Translate -> Export`. | `.pdf`, `.docx`, `.md`, `.png`, `.jpg`, etc. | `.md`, `.zip`, `.html` | `MarkdownBasedWorkflowConfig` |
| **`TXTWorkflow`** | Processes plain text documents. Flow: `txt -> Translate -> Export`. | `.txt` and other plain text formats | `.txt`, `.html` | `TXTWorkflowConfig` | | **`TXTWorkflow`** | Processes plain text documents. Flow: `txt -> Translate -> Export`. | `.txt` and other plain text formats | `.txt`, `.html` | `TXTWorkflowConfig` |
| **`JsonWorkflow`** | Processes JSON files. Flow: `json -> Translate -> Export`. | `.json` | `.json`, `.html` | `JsonWorkflowConfig` | | **`JsonWorkflow`** | Processes JSON files. Flow: `json -> Translate -> Export`. | `.json` | `.json`, `.html` | `JsonWorkflowConfig` |
| **`DocxWorkflow`** | Processes docx files. Flow: `docx -> Translate -> Export`. | `.docx` | `.docx`, `.html` | `DocxWorkflowConfig` | | **`DocxWorkflow`** | Processes docx files. Flow: `docx -> Translate -> Export`. | `.docx` | `.docx`, `.html` | `DocxWorkflowConfig` |
| **`XlsxWorkflow`** | Processes xlsx files. Flow: `xlsx -> Translate -> Export`. | `.xlsx`, `.csv` | `.xlsx`, `.html` | `XlsxWorkflowConfig` | | **`XlsxWorkflow`** | Processes xlsx files. Flow: `xlsx -> Translate -> Export`. | `.xlsx`, `.csv` | `.xlsx`, `.html` | `XlsxWorkflowConfig` |
| **`SrtWorkflow`** | Processes srt files. Flow: `srt -> Translate -> Export`. | `.srt` | `.srt`, `.html` | `SrtWorkflowConfig` | | **`SrtWorkflow`** | Processes srt files. Flow: `srt -> Translate -> Export`. | `.srt` | `.srt`, `.html` | `SrtWorkflowConfig` |
| **`EpubWorkflow`** | Processes epub files. Flow: `epub -> Translate -> Export`. | `.epub` | `.epub`, `.html` | `EpubWorkflowConfig` | | **`EpubWorkflow`** | Processes epub files. Flow: `epub -> Translate -> Export`. | `.epub` | `.epub`, `.html` | `EpubWorkflowConfig` |
| **`HtmlWorkflow`** | Processes html files. Flow: `html -> Translate -> Export`. | `.html`, `.htm` | `.html` | `HtmlWorkflowConfig` | | **`HtmlWorkflow`** | Processes html files. Flow: `html -> Translate -> Export`. | `.html`, `.htm` | `.html` | `HtmlWorkflowConfig` |
> You can export to PDF format in the interactive interface. > You can export to PDF format in the interactive interface.
@@ -136,14 +152,16 @@ export DOCUTRANSLATE_PORT=8011
docutranslate -i docutranslate -i
``` ```
- **Interactive Interface**: After starting the service, visit `http://127.0.0.1:8010` (or your specified port) in your browser. - **Interactive Interface**: After starting the service, visit `http://127.0.0.1:8010` (or your specified port) in your
- **API Documentation**: The complete API documentation (Swagger UI) is available at `http://127.0.0.1:8010/docs`. browser.
- **API Documentation**: The complete API documentation (Swagger UI) is available at `http://127.0.0.1:8010/docs`.
## Usage ## Usage
### Example 1: Translate a PDF file (using `MarkdownBasedWorkflow`) ### Example 1: Translate a PDF file (using `MarkdownBasedWorkflow`)
This is the most common use case. We will use the `minerU` engine to convert the PDF to Markdown and then use an LLM for translation. This example uses the asynchronous method. This is the most common use case. We will use the `minerU` engine to convert the PDF to Markdown and then use an LLM for
translation. This example uses the asynchronous method.
```python ```python
import asyncio import asyncio
@@ -210,7 +228,8 @@ if __name__ == "__main__":
### Example 2: Translate a TXT file (using `TXTWorkflow`) ### Example 2: Translate a TXT file (using `TXTWorkflow`)
For plain text files, the process is simpler as it doesn't require a document parsing (conversion) step. This example uses the asynchronous method. For plain text files, the process is simpler as it doesn't require a document parsing (conversion) step. This example
uses the asynchronous method.
```python ```python
import asyncio import asyncio
@@ -257,7 +276,8 @@ if __name__ == "__main__":
### Example 3: Translate a JSON file (using `JsonWorkflow`) ### Example 3: Translate a JSON file (using `JsonWorkflow`)
This example uses the asynchronous method. The `json_paths` item in `JsonTranslatorConfig` needs to specify the JSON paths to be translated (conforming to the `jsonpath-ng` syntax). Only values matching these paths will be translated. This example uses the asynchronous method. The `json_paths` item in `JsonTranslatorConfig` needs to specify the JSON
paths to be translated (conforming to the `jsonpath-ng` syntax). Only values matching these paths will be translated.
```python ```python
import asyncio import asyncio
@@ -404,32 +424,87 @@ if __name__ == "__main__":
asyncio.run(main()) asyncio.run(main())
``` ```
### Example 5: Configuration Items for Other Workflows (Using `HtmlWorkflow`, `EpubWorkflow`)
Here is an example using asynchronous mode.
```python
# HtmlWorkflow
from docutranslate.translator.ai_translator.html_translator import HtmlTranslatorConfig
from docutranslate.workflow.html_workflow import HtmlWorkflowConfig, HtmlWorkflow
async def html():
# 1. Create translator configuration
translator_config = HtmlTranslatorConfig(
base_url="https://api.openai.com/v1/",
api_key="YOUR_OPENAI_API_KEY",
model_id="gpt-4o",
to_lang="Chinese",
insert_mode="replace", # Options: "replace", "append", "prepend"
separator="\n", # Separator used for "append" and "prepend" modes
)
# 2. Create main workflow configuration
workflow_config = HtmlWorkflowConfig(
translator_config=translator_config,
)
workflow_html = HtmlWorkflow(config=workflow_config)
# EpubWorkflow
from docutranslate.exporter.epub.epub2html_exporter import Epub2HTMLExporterConfig
from docutranslate.translator.ai_translator.epub_translator import EpubTranslatorConfig
from docutranslate.workflow.epub_workflow import EpubWorkflowConfig, EpubWorkflow
async def epub():
# 1. Create translator configuration
translator_config = EpubTranslatorConfig(
base_url="https://api.openai.com/v1/",
api_key="YOUR_OPENAI_API_KEY",
model_id="gpt-4o",
to_lang="Chinese",
insert_mode="replace", # Options: "replace", "append", "prepend"
separator="\n", # Separator used for "append" and "prepend" modes
)
# 2. Create main workflow configuration
workflow_config = EpubWorkflowConfig(
translator_config=translator_config,
html_exporter_config=Epub2HTMLExporterConfig(cdn=True),
)
workflow_epub = EpubWorkflow(config=workflow_config)
```
## Prerequisites and Configuration Details ## Prerequisites and Configuration Details
### 1. Get a Large Model API Key ### 1. Get a Large Model API Key
The translation feature relies on large language models. You need to obtain a `base_url`, `api_key`, and `model_id` from the respective AI platform. The translation feature relies on large language models. You need to obtain a `base_url`, `api_key`, and `model_id` from
the respective AI platform.
> Recommended models: Volcengine's `doubao-seed-1-6-flash` and `doubao-seed-1-6` series, Zhipu's `glm-4-flash`, Alibaba Cloud's `qwen-plus` and `qwen-flash`, Deepseek's `deepseek-chat`, etc. > Recommended models: Volcengine's `doubao-seed-1-6-flash` and `doubao-seed-1-6` series, Zhipu's `glm-4-flash`, Alibaba
> Cloud's `qwen-plus` and `qwen-flash`, Deepseek's `deepseek-chat`, etc.
> [302.AI](https://share.302.ai/BgRLAe)👈 Register through this link to enjoy a $1 free credit > [302.AI](https://share.302.ai/BgRLAe)👈 Register through this link to enjoy a $1 free credit
| Platform Name | Get API Key | Base URL | | Platform Name | Get API Key | Base URL |
|:--------------------|:-----------------------------------------------------------------------------------------|:---------------------------------------------------------| |:------------------------------|:----------------------------------------------------------------------------------------------|:-----------------------------------------------------------|
| ollama | | `http://127.0.0.1:11434/v1` | | ollama | | `http://127.0.0.1:11434/v1` |
| lm studio | | `http://127.0.0.1:1234/v1` | | lm studio | | `http://127.0.0.1:1234/v1` |
| 302.AI | [Click to get](https://share.302.ai/BgRLAe) | `https://api.302.ai/v1` | | 302.AI | [Click to get](https://share.302.ai/BgRLAe) | `https://api.302.ai/v1` |
| openrouter | [Click to get](https://openrouter.ai/settings/keys) | `https://openrouter.ai/api/v1` | | openrouter | [Click to get](https://openrouter.ai/settings/keys) | `https://openrouter.ai/api/v1` |
| openai | [Click to get](https://platform.openai.com/api-keys) | `https://api.openai.com/v1/` | | openai | [Click to get](https://platform.openai.com/api-keys) | `https://api.openai.com/v1/` |
| gemini | [Click to get](https://aistudio.google.com/u/0/apikey) | `https://generativelanguage.googleapis.com/v1beta/openai/` | | gemini | [Click to get](https://aistudio.google.com/u/0/apikey) | `https://generativelanguage.googleapis.com/v1beta/openai/` |
| deepseek | [Click to get](https://platform.deepseek.com/api_keys) | `https://api.deepseek.com/v1` | | deepseek | [Click to get](https://platform.deepseek.com/api_keys) | `https://api.deepseek.com/v1` |
| Zhipu AI (智谱ai) | [Click to get](https://open.bigmodel.cn/usercenter/apikeys) | `https://open.bigmodel.cn/api/paas/v4` | | Zhipu AI (智谱ai) | [Click to get](https://open.bigmodel.cn/usercenter/apikeys) | `https://open.bigmodel.cn/api/paas/v4` |
| Tencent Hunyuan (腾讯混元) | [Click to get](https://console.cloud.tencent.com/hunyuan/api-key) | `https://api.hunyuan.cloud.tencent.com/v1` | | Tencent Hunyuan (腾讯混元) | [Click to get](https://console.cloud.tencent.com/hunyuan/api-key) | `https://api.hunyuan.cloud.tencent.com/v1` |
| Alibaba Cloud Bailian (阿里云百炼) | [Click to get](https://bailian.console.aliyun.com/?tab=model#/api-key) | `https://dashscope.aliyuncs.com/compatible-mode/v1` | | Alibaba Cloud Bailian (阿里云百炼) | [Click to get](https://bailian.console.aliyun.com/?tab=model#/api-key) | `https://dashscope.aliyuncs.com/compatible-mode/v1` |
| Volcengine (火山引擎) | [Click to get](https://console.volcengine.com/ark/region:ark+cn-beijing/apiKey?apikey=%7B%7D) | `https://ark.cn-beijing.volces.com/api/v3` | | Volcengine (火山引擎) | [Click to get](https://console.volcengine.com/ark/region:ark+cn-beijing/apiKey?apikey=%7B%7D) | `https://ark.cn-beijing.volces.com/api/v3` |
| SiliconFlow (硅基流动) | [Click to get](https://cloud.siliconflow.cn/account/ak) | `https://api.siliconflow.cn/v1` | | SiliconFlow (硅基流动) | [Click to get](https://cloud.siliconflow.cn/account/ak) | `https://api.siliconflow.cn/v1` |
| DMXAPI | [Click to get](https://www.dmxapi.cn/token) | `https://www.dmxapi.cn/v1` | | DMXAPI | [Click to get](https://www.dmxapi.cn/token) | `https://www.dmxapi.cn/v1` |
| Juguang AI (聚光AI) | [Click to get](https://ai.juguang.chat/console/token) | `https://ai.juguang.chat/v1` | | Juguang AI (聚光AI) | [Click to get](https://ai.juguang.chat/console/token) | `https://ai.juguang.chat/v1` |
### 2. PDF Parsing Engine (ignore if not translating PDFs) ### 2. PDF Parsing Engine (ignore if not translating PDFs)
@@ -437,37 +512,45 @@ The translation feature relies on large language models. You need to obtain a `b
If you choose `mineru` as your document parsing engine (`convert_engine="mineru"`), you need to apply for a free token. If you choose `mineru` as your document parsing engine (`convert_engine="mineru"`), you need to apply for a free token.
1. Visit the [minerU official website](https://mineru.net/apiManage/docs) to register and apply for an API. 1. Visit the [minerU official website](https://mineru.net/apiManage/docs) to register and apply for an API.
2. Create a new API Token in the [API Token Management interface](https://mineru.net/apiManage/token). 2. Create a new API Token in the [API Token Management interface](https://mineru.net/apiManage/token).
> **Note**: minerU Tokens are valid for 14 days. Please create a new one after expiration. > **Note**: minerU Tokens are valid for 14 days. Please create a new one after expiration.
#### 2.2. docling Engine Configuration (Local PDF parsing) #### 2.2. docling Engine Configuration (Local PDF parsing)
If you choose `docling` as your document parsing engine (`convert_engine="docling"`), it will download the required models from Hugging Face upon first use. If you choose `docling` as your document parsing engine (`convert_engine="docling"`), it will download the required
models from Hugging Face upon first use.
> A better option is to download `docling_artifact.zip` from [GitHub Releases](https://github.com/xunbu/docutranslate/releases) and extract it to your working directory. > A better option is to download `docling_artifact.zip`
> from [GitHub Releases](https://github.com/xunbu/docutranslate/releases) and extract it to your working directory.
**Solutions for network issues when downloading `docling` models:** **Solutions for network issues when downloading `docling` models:**
1. **Set a Hugging Face mirror (Recommended)**: 1. **Set a Hugging Face mirror (Recommended)**:
* **Method A (Environment Variable)**: Set the system environment variable `HF_ENDPOINT` and restart your IDE or terminal. * **Method A (Environment Variable)**: Set the system environment variable `HF_ENDPOINT` and restart your IDE or
``` terminal.
HF_ENDPOINT=https://hf-mirror.com ```
``` HF_ENDPOINT=https://hf-mirror.com
* **Method B (Set in code)**: Add the following code at the beginning of your Python script. ```
* **Method B (Set in code)**: Add the following code at the beginning of your Python script.
```python ```python
import os import os
os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com' os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
``` ```
2. **Offline Usage (Download the model package in advance)**:
* Download `docling_artifact.zip` from [GitHub Releases](https://github.com/xunbu/docutranslate/releases). 2. **Offline Usage (Download the model package in advance)**:
* Extract it into your project directory. * Download `docling_artifact.zip` from [GitHub Releases](https://github.com/xunbu/docutranslate/releases).
* Specify the model path in your configuration (if the model is not in the same directory as the script): * Extract it into your project directory.
* Specify the model path in your configuration (if the model is not in the same directory as the script):
```python ```python
from docutranslate.converter.x2md.converter_docling import ConverterDoclingConfig from docutranslate.converter.x2md.converter_docling import ConverterDoclingConfig
converter_config = ConverterDoclingConfig( converter_config = ConverterDoclingConfig(
artifact="./docling_artifact", # Path to the extracted folder artifact="./docling_artifact", # Path to the extracted folder
code_ocr=True, code_ocr=True,
@@ -478,7 +561,8 @@ converter_config = ConverterDoclingConfig(
## FAQ ## FAQ
**Q: Why is the translated text still in the original language?** **Q: Why is the translated text still in the original language?**
A: Check the logs for errors. It's usually due to an overdue payment on the AI platform or network issues (check if you need to enable the system proxy). A: Check the logs for errors. It's usually due to an overdue payment on the AI platform or network issues (check if you
need to enable the system proxy).
**Q: Port 8010 is already in use. What should I do?** **Q: Port 8010 is already in use. What should I do?**
A: Use the `-p` parameter to specify a new port, or set the `DOCUTRANSLATE_PORT` environment variable. A: Use the `-p` parameter to specify a new port, or set the `DOCUTRANSLATE_PORT` environment variable.
@@ -487,18 +571,25 @@ A: Use the `-p` parameter to specify a new port, or set the `DOCUTRANSLATE_PORT`
A: Yes. Please use the `mineru` parsing engine, which has powerful OCR capabilities. A: Yes. Please use the `mineru` parsing engine, which has powerful OCR capabilities.
**Q: Why is the first PDF translation very slow?** **Q: Why is the first PDF translation very slow?**
A: If you are using the `docling` engine, it needs to download models from Hugging Face on its first run. Please refer to the "Network Issues Solutions" section above to speed up this process. A: If you are using the `docling` engine, it needs to download models from Hugging Face on its first run. Please refer
to the "Network Issues Solutions" section above to speed up this process.
**Q: How can I use it in an intranet (offline) environment?** **Q: How can I use it in an intranet (offline) environment?**
A: Absolutely. You need to meet the following conditions: A: Absolutely. You need to meet the following conditions:
1. **Local LLM**: Deploy a language model locally using tools like [Ollama](https://ollama.com/) or [LM Studio](https://lmstudio.ai/), and fill in the local model's `base_url` in `TranslatorConfig`.
2. **Local PDF Parsing Engine** (only for parsing PDFs): Use the `docling` engine and download the model package in advance as described in the "Offline Usage" section above. 1. **Local LLM**: Deploy a language model locally using tools like [Ollama](https://ollama.com/)
or [LM Studio](https://lmstudio.ai/), and fill in the local model's `base_url` in `TranslatorConfig`.
2. **Local PDF Parsing Engine** (only for parsing PDFs): Use the `docling` engine and download the model package in
advance as described in the "Offline Usage" section above.
**Q: How does the PDF parsing cache mechanism work?** **Q: How does the PDF parsing cache mechanism work?**
A: `MarkdownBasedWorkflow` automatically caches the results of document parsing (file-to-Markdown conversion) to avoid repetitive, time-consuming parsing. The cache is stored in memory by default and records the last 10 parses. You can change the cache size using the `DOCUTRANSLATE_CACHE_NUM` environment variable. A: `MarkdownBasedWorkflow` automatically caches the results of document parsing (file-to-Markdown conversion) to avoid
repetitive, time-consuming parsing. The cache is stored in memory by default and records the last 10 parses. You can
change the cache size using the `DOCUTRANSLATE_CACHE_NUM` environment variable.
**Q: How can I make the software use a proxy?** **Q: How can I make the software use a proxy?**
A: By default, the software does not use the system proxy. You can enable it by setting `system_proxy_enable=True` in `TranslatorConfig`. A: By default, the software does not use the system proxy. You can enable it by setting `system_proxy_enable=True` in
`TranslatorConfig`.
## Star History ## Star History

58
README_JP.md
View File

@@ -411,13 +411,67 @@ if __name__ == "__main__":
asyncio.run(main()) asyncio.run(main())
``` ```
### 例 5: その他のワークフローの設定項目 (`HtmlWorkflow`、`EpubWorkflow` の使用)
以下は非同期モードの使用例です。
```python
# HtmlWorkflow
from docutranslate.translator.ai_translator.html_translator import HtmlTranslatorConfig
from docutranslate.workflow.html_workflow import HtmlWorkflowConfig, HtmlWorkflow
async def html():
# 1. 翻訳機の設定を作成
translator_config = HtmlTranslatorConfig(
base_url="https://api.openai.com/v1/",
api_key="YOUR_OPENAI_API_KEY",
model_id="gpt-4o",
to_lang="中国語",
insert_mode="replace", # 選択肢: "replace", "append", "prepend"
separator="\n", # "append", "prepend" モードで使用される区切り文字
)
# 2. メインワークフローの設定を作成
workflow_config = HtmlWorkflowConfig(
translator_config=translator_config,
)
workflow_html = HtmlWorkflow(config=workflow_config)
# EpubWorkflow
from docutranslate.exporter.epub.epub2html_exporter import Epub2HTMLExporterConfig
from docutranslate.translator.ai_translator.epub_translator import EpubTranslatorConfig
from docutranslate.workflow.epub_workflow import EpubWorkflowConfig, EpubWorkflow
async def epub():
# 1. 翻訳機の設定を作成
translator_config = EpubTranslatorConfig(
base_url="https://api.openai.com/v1/",
api_key="YOUR_OPENAI_API_KEY",
model_id="gpt-4o",
to_lang="中国語",
insert_mode="replace", # 選択肢: "replace", "append", "prepend"
separator="\n", # "append", "prepend" モードで使用される区切り文字
)
# 2. メインワークフローの設定を作成
workflow_config = EpubWorkflowConfig(
translator_config=translator_config,
html_exporter_config=Epub2HTMLExporterConfig(cdn=True),
)
workflow_epub = EpubWorkflow(config=workflow_config)
```
## 前提条件と設定詳細 ## 前提条件と設定詳細
### 1. 大規模モデルAPIキーの取得 ### 1. 大規模モデルAPIキーの取得
翻訳機能は大規模言語モデルに依存しているため、対応するAIプラットフォームから`base_url`、`api_key`、`model_id`を取得する必要があります。 翻訳機能は大規模言語モデルに依存しているため、対応するAIプラットフォームから`base_url`、`api_key`、`model_id`を取得する必要があります。
> 推奨モデル：火山引擎の`doubao-seed-1-6-flash`、`doubao-seed-1-6`シリーズ、智譜の`glm-4-flash`、阿里雲の`qwen-plus`、 `qwen-flash`、deepseekの`deepseek-chat`など。 > 推奨モデル：火山引擎の`doubao-seed-1-6-flash`、`doubao-seed-1-6`シリーズ、智譜の`glm-4-flash`、阿里雲の`qwen-plus`、
`qwen-flash`、deepseekの`deepseek-chat`など。
> [302.AI](https://share.302.ai/BgRLAe)👈 このリンクから登録で1ドル分の無料クレジットを提供 > [302.AI](https://share.302.ai/BgRLAe)👈 このリンクから登録で1ドル分の無料クレジットを提供
@@ -425,7 +479,7 @@ if __name__ == "__main__":
|:-----------|:---------------------------------------------------------------------------------------------|:-----------------------------------------------------------| |:-----------|:---------------------------------------------------------------------------------------------|:-----------------------------------------------------------|
| ollama | | `http://127.0.0.1:11434/v1` | | ollama | | `http://127.0.0.1:11434/v1` |
| lm studio | | `http://127.0.0.1:1234/v1` | | lm studio | | `http://127.0.0.1:1234/v1` |
| 302.AI | [ここをクリックして取得](https://share.302.ai/BgRLAe) | `https://api.302.ai/v1` | | 302.AI | [ここをクリックして取得](https://share.302.ai/BgRLAe) | `https://api.302.ai/v1` |
| openrouter | [ここをクリックして取得](https://openrouter.ai/settings/keys) | `https://openrouter.ai/api/v1` | | openrouter | [ここをクリックして取得](https://openrouter.ai/settings/keys) | `https://openrouter.ai/api/v1` |
| openai | [ここをクリックして取得](https://platform.openai.com/api-keys) | `https://api.openai.com/v1/` | | openai | [ここをクリックして取得](https://platform.openai.com/api-keys) | `https://api.openai.com/v1/` |
| gemini | [ここをクリックして取得](https://aistudio.google.com/u/0/apikey) | `https://generativelanguage.googleapis.com/v1beta/openai/` | | gemini | [ここをクリックして取得](https://aistudio.google.com/u/0/apikey) | `https://generativelanguage.googleapis.com/v1beta/openai/` |

56
README_ZH.md
View File

@@ -406,13 +406,67 @@ if __name__ == "__main__":
asyncio.run(main()) asyncio.run(main())
``` ```
### 示例 5: 其它workflow的配置项(使用 `HtmlWorkflow`、`EpubWorkflow`)
这里以异步方式为例。
```python
# HtmlWorkflow
from docutranslate.translator.ai_translator.html_translator import HtmlTranslatorConfig
from docutranslate.workflow.html_workflow import HtmlWorkflowConfig, HtmlWorkflow
async def html():
# 1. 构建翻译器配置
translator_config = HtmlTranslatorConfig(
base_url="https://api.openai.com/v1/",
api_key="YOUR_OPENAI_API_KEY",
model_id="gpt-4o",
to_lang="中文",
insert_mode="replace", # 备选项 "replace", "append", "prepend"
separator="\n", # "append", "prepend"模式时使用的分隔符
)
# 2. 构建主工作流配置
workflow_config = HtmlWorkflowConfig(
translator_config=translator_config,
)
workflow_html = HtmlWorkflow(config=workflow_config)
# EpubWorkflow
from docutranslate.exporter.epub.epub2html_exporter import Epub2HTMLExporterConfig
from docutranslate.translator.ai_translator.epub_translator import EpubTranslatorConfig
from docutranslate.workflow.epub_workflow import EpubWorkflowConfig, EpubWorkflow
async def epub():
# 1. 构建翻译器配置
translator_config = EpubTranslatorConfig(
base_url="https://api.openai.com/v1/",
api_key="YOUR_OPENAI_API_KEY",
model_id="gpt-4o",
to_lang="中文",
insert_mode="replace", # 备选项 "replace", "append", "prepend"
separator="\n", # "append", "prepend"模式时使用的分隔符
)
# 2. 构建主工作流配置
workflow_config = EpubWorkflowConfig(
translator_config=translator_config,
html_exporter_config=Epub2HTMLExporterConfig(cdn=True),
)
workflow_epub = EpubWorkflow(config=workflow_config)
```
## 前置条件与配置详解 ## 前置条件与配置详解
### 1. 获取大模型 API Key ### 1. 获取大模型 API Key
翻译功能依赖于大型语言模型，您需要从相应的 AI 平台获取 `base_url`, `api_key` 和 `model_id`。 翻译功能依赖于大型语言模型，您需要从相应的 AI 平台获取 `base_url`, `api_key` 和 `model_id`。
> 推荐模型：火山引擎的`doubao-seed-1-6-flash`、`doubao-seed-1-6`系列、智谱的`glm-4-flash`，阿里云的 `qwen-plus`、`qwen-flash`，deepseek的`deepseek-chat`等。 > 推荐模型：火山引擎的`doubao-seed-1-6-flash`、`doubao-seed-1-6`系列、智谱的`glm-4-flash`，阿里云的 `qwen-plus`、`qwen-flash`
> ，deepseek的`deepseek-chat`等。
> [302.AI](https://share.302.ai/BgRLAe)👈从该链接注册可享1美元免费额度 > [302.AI](https://share.302.ai/BgRLAe)👈从该链接注册可享1美元免费额度