update doc

This commit is contained in:
musistudio
2025-07-30 14:50:45 +08:00
parent c02e314d76
commit 74fa03d3a5
3 changed files with 20 additions and 2 deletions

View File

@@ -250,6 +250,11 @@ Transformers allow you to modify the request and response payloads to ensure com
- `maxtoken`: Sets a specific `max_tokens` value. - `maxtoken`: Sets a specific `max_tokens` value.
- `tooluse`: Optimizes tool usage for certain models via `tool_choice`. - `tooluse`: Optimizes tool usage for certain models via `tool_choice`.
- `gemini-cli` (experimental): Unofficial support for Gemini via Gemini CLI [gemini-cli.js](https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd). - `gemini-cli` (experimental): Unofficial support for Gemini via Gemini CLI [gemini-cli.js](https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd).
- `reasoning`: Used to process the `reasoning_content` field.
- `sampling`: Used to process sampling information fields such as `temperature`, `top_p`, `top_k`, and `repetition_penalty`.
- `enhancetool`: Adds a layer of error tolerance to the tool call parameters returned by the LLM (this will cause the tool call information to no longer be streamed).
- `cleancache`: Clears the `cache_control` field from requests.
- `vertex-gemini`: Handles the Gemini API using Vertex authentication.
**Custom Transformers:** **Custom Transformers:**
@@ -440,5 +445,9 @@ A huge thank you to all our sponsors for their generous support!
- [@congzhangzh](https://github.com/congzhangzh) - [@congzhangzh](https://github.com/congzhangzh)
- @\*\_ - @\*\_
- @Z\*m - @Z\*m
- @*鑫
- @c\*y
- @\*昕
(If your name is masked, please contact me via my homepage email to update it with your GitHub username.) (If your name is masked, please contact me via my homepage email to update it with your GitHub username.)

View File

@@ -245,6 +245,11 @@ Transformers 允许您修改请求和响应负载,以确保与不同提供商
- `maxtoken`: 设置特定的 `max_tokens` 值。 - `maxtoken`: 设置特定的 `max_tokens` 值。
- `tooluse`: 优化某些模型的工具使用(通过`tool_choice`参数)。 - `tooluse`: 优化某些模型的工具使用(通过`tool_choice`参数)。
- `gemini-cli` (实验性): 通过 Gemini CLI [gemini-cli.js](https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd) 对 Gemini 的非官方支持。 - `gemini-cli` (实验性): 通过 Gemini CLI [gemini-cli.js](https://gist.github.com/musistudio/1c13a65f35916a7ab690649d3df8d1cd) 对 Gemini 的非官方支持。
- `reasoning`: 用于处理 `reasoning_content` 字段。
- `sampling`: 用于处理采样信息字段,如 `temperature`、`top_p`、`top_k` 和 `repetition_penalty`。
- `enhancetool`: 对 LLM 返回的工具调用参数增加一层容错处理(这会导致不再流式返回工具调用信息)。
- `cleancache`: 清除请求中的 `cache_control` 字段。
- `vertex-gemini`: 处理使用 vertex 鉴权的 gemini api。
**自定义 Transformer:** **自定义 Transformer:**
@@ -435,6 +440,9 @@ jobs:
- [@congzhangzh](https://github.com/congzhangzh) - [@congzhangzh](https://github.com/congzhangzh)
- @*_ - @*_
- @Z\*m - @Z\*m
- @*鑫
- @c\*y
- @\*昕
(如果您的名字被屏蔽,请通过我的主页电子邮件与我联系,以便使用您的 GitHub 用户名进行更新。) (如果您的名字被屏蔽,请通过我的主页电子邮件与我联系,以便使用您的 GitHub 用户名进行更新。)

5
package-lock.json generated
View File

@@ -10,7 +10,7 @@
"license": "MIT", "license": "MIT",
"dependencies": { "dependencies": {
"@fastify/static": "^8.2.0", "@fastify/static": "^8.2.0",
"@musistudio/llms": "file:../llms", "@musistudio/llms": "^1.0.16",
"dotenv": "^16.4.7", "dotenv": "^16.4.7",
"json5": "^2.2.3", "json5": "^2.2.3",
"openurl": "^1.1.1", "openurl": "^1.1.1",
@@ -30,7 +30,7 @@
}, },
"../llms": { "../llms": {
"name": "@musistudio/llms", "name": "@musistudio/llms",
"version": "1.0.15", "version": "1.0.16",
"license": "MIT", "license": "MIT",
"dependencies": { "dependencies": {
"@anthropic-ai/sdk": "^0.54.0", "@anthropic-ai/sdk": "^0.54.0",
@@ -40,6 +40,7 @@
"fastify": "^5.4.0", "fastify": "^5.4.0",
"google-auth-library": "^10.1.0", "google-auth-library": "^10.1.0",
"json5": "^2.2.3", "json5": "^2.2.3",
"jsonrepair": "^3.13.0",
"openai": "^5.6.0", "openai": "^5.6.0",
"undici": "^7.10.0", "undici": "^7.10.0",
"uuid": "^11.1.0" "uuid": "^11.1.0"