mirror of
https://github.com/deepseek-ai/deepseek-recipe.git
synced 2026-10-26 16:55:05 +00:00
docs: update project documentation
This commit is contained in:
1 parent
57b9c84242
commit
8cadfede70
3 files changed
+6
-7
No files matched your search
@@ -13,14 +13,13 @@ into responses in the corresponding format. Use these components to connect an
|
||||
inference backend to API services that support multiple formats. Model
|
||||
inference, tool execution, and HTTP transport must be provided externally.
|
||||
|
||||
[Getting started](#using-deepseek-recipe) · [Streaming](docs/streaming.md) ·
|
||||
[Use with tokenizer](docs/tokenizer.md) · [Contributing](CONTRIBUTING.md) ·
|
||||
[License](#license)
|
||||
[Getting started](#using-deepseek-recipe) · [Streaming response](docs/streaming.md) ·
|
||||
[Use with tokenizer](docs/tokenizer.md) · [License](#license)
|
||||
|
||||
## Supported scope
|
||||
|
||||
- **Request/response formats:** Conversion of Messages, Chat Completions, and
|
||||
Responses requests, [streamed responses](docs/streaming.md), and complete
|
||||
Responses requests, [Streaming response](docs/streaming.md), and complete
|
||||
responses. Supports text, images, thinking, and client tool calls.
|
||||
- **Prompts:** Encoding of DeepSeek V4 and V4.1 conversations into prompts or token IDs.
|
||||
- **Generation settings:** Thinking mode, reasoning effort, `temperature`, `top_p`,
|
||||
@@ -114,7 +113,7 @@ Open [http://127.0.0.1:7778](http://127.0.0.1:7778).
|
||||
### More examples
|
||||
|
||||
Rust and Python both support converting model output into streaming responses.
|
||||
See the [streaming examples](docs/streaming.md). To encode conversations into
|
||||
See the [Streaming response](docs/streaming.md). To encode conversations into
|
||||
token IDs or decode backend token IDs, see
|
||||
[use with tokenizer](docs/tokenizer.md).
|
||||
|
||||
|
||||
+1
-1
@@ -9,7 +9,7 @@
|
||||
deepseek-recipe 包含一套 Rust 库以及对应的 Python bindings:支持将不同格式的 API 请求统一转换为 Conversation 格式,编码成适用于 DeepSeek 模型的 prompt,并支持将模型输出转换为对应格式的响应。
|
||||
可用于把推理后端接入兼容多种格式的 API 服务;模型推理、工具执行和 HTTP 传输需由外部提供。
|
||||
|
||||
[快速上手](#使用-deepseek-recipe) · [流式响应](docs/streaming.zh.md) · [使用 tokenizer](docs/tokenizer.zh.md) · [贡献指南](CONTRIBUTING.md) · [许可证](#许可证)
|
||||
[快速上手](#使用-deepseek-recipe) · [流式响应](docs/streaming.zh.md) · [使用 tokenizer](docs/tokenizer.zh.md) · [许可证](#许可证)
|
||||
|
||||
## 支持范围
|
||||
|
||||
|
||||
+1
-1
@@ -1,4 +1,4 @@
|
||||
# Response streaming
|
||||
# Streaming response
|
||||
|
||||
**English** | [中文](streaming.zh.md)
|
||||
|
||||
|
||||
Reference in new issue
Block a user