Use the AutoGLM Image Recognition API to analyze and describe image content. Use this skill when the user needs image analysis, object or scene recognition,...
Design & media
Autoglm File Upload
Try itUse the AutoGLM Upload Mix API to upload local files such as images and documents, then obtain a file URL or resource ID for downstream API calls. The token...
What it does
Use the AutoGLM Upload Mix API to upload local files such as images and documents, then obtain a file URL or resource ID for downstream API calls. The token is fetched automatically from the local service at http://127.0.0.1:18432/get_token, so no manual environment variable setup is required.
The skill document
AutoGLM File Upload Skill
Upload a local file to the AutoGLM server and return file resource information that can be used by other APIs.
Token Retrieval
When the script starts, it automatically sends an HTTP GET request to the local service to retrieve a token:
| Item | Value |
|---|---|
| URL | http://127.0.0.1:18432/get_token |
| Method | GET |
| Response | Bearer xxx (used directly as the Authorization header) |
If the returned token does not include the
Bearerprefix, the script adds it automatically.
Upload Mix API
| Item | Value |
|---|---|
| URL | https://autoglm-api.autoglm.ai/agentdr/v1/assistant/upload-mix |
| Method | POST |
| Request body | multipart/form-data, with the field name files |
Signed headers (generated dynamically for each request):
X-Auth-Appid:100003X-Auth-TimeStamp: current Unix timestamp in secondsX-Auth-Sign: MD5(100003 + "&" + timestamp + "&" + 38d2391985e2369a5fb8227d8e6cd5e5)
Run the Script
Use upload-mix.py in the same directory:
python upload-mix.py ""
Examples:
# Upload an image
python upload-mix.py "/path/to/image.jpg"
# Upload a document
python upload-mix.py "/path/to/document.pdf"
The script automatically detects the file's MIME type and includes it in the request.
Response Handling
Response Structure
{
"code": 0,
"msg": "SUCCESS",
"time": 1773199477734,
"trace": "78dd001f3ec04c37b6a1d58b5db70fce",
"data": {
"message": "",
"oss_info": [
{
"filename": "SKILL.md",
"oss_name": "auto_fly/8a4e6ab6-c2ab-4e88-b4af-fb62db9379af/SKILL.md",
"oss_url": "https://autoglm-agent.aminer.cn/auto_fly/8a4e6ab6-c2ab-4e88-b4af-fb62db9379af/SKILL.md"
}
]
}
}
Output Requirements
1. Extract the file URL
Use data.oss_info[0].oss_url as the uploaded file URL. It can be passed directly to downstream APIs such as the image_url parameter in image-recognition.
2. Typical follow-up flow
upload_mix (upload a local file) -> get the URL -> image_recognition (analyze the image)
Related skills
Call the GLM API (GLM 5 and 4 series) through RunAPI using OpenAI-compatible Chat Completions. Use for GLM text chat, streaming, or an existing compatibility client that needs the conditional reference.
Generate images from prompts across OpenAI, Azure, Google, DashScope, Seedream, Jimeng and more, with batch mode.
Use this skill when you need to publish, fetch, search, list, share, or watch AgentFiles artifacts from Codex, Claude Code, OpenClaw, or other agent runtimes...
通过 Flyelep 开放接口把本地图片、视频、音频上传到云存储,返回可公网访问的直链。 当用户提供的是本地文件而不是 URL,或需要为其它 Flyelep 技能准备 imgUrls(抠图、翻译、延展、局部重绘等)、 referenceImageStr / referenceVideoStr / referenceAudioStr(生成视频)入参时使用此技能。
Terminal transcription of audio files and URLs with the Gladia CLI (gladia speech-to-text). Use when the user has gladia-cli installed, wants shell-based tra...