Gemini Embedding 001 Serverless API

 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "gemini-embedding-001",
 9    input="Segmind provides fast and affordable AI model inference APIs for image, video, audio, and text generation.",
10    task_type="RETRIEVAL_DOCUMENT",
11)
12print(result["status"])                      # COMPLETED
13print(result.get("output"))                  # model output (e.g. media URL)
14print(result["metrics"]["inference_time"])   # server compute seconds
15
16# --- Or submit + poll manually (track request_id, control the cadence) ---
17from segmind import SegmindClient, InferenceFailed, InferenceTimeout
18
19client = SegmindClient()                      # reads SEGMIND_API_KEY
20payload = {
21    "input": "Segmind provides fast and affordable AI model inference APIs for image, video, audio, and text generation.",
22    "task_type": "RETRIEVAL_DOCUMENT",
23}
24job = client.submit_async("gemini-embedding-001", **payload)
25print(job.request_id)                         # available immediately
26try:
27    result = job.wait(timeout=600, interval=1.0)
28except InferenceTimeout as e:
29    print("still running:", e.request_id)
30except InferenceFailed as e:
31    print("failed:", e.detail)