Gawe embeddings teks
Nggawe embeddings teks nganggo ShareAI kanggo telusuran semantik, pengambilan lan kemiripan, kanthi format input sing didhukung lan syarat model.
Ing kaca iki
https://api.shareai.now/api/v1/embeddingsNgonversi siji utawa luwih teks dadi vektor embedding.
- URL Dasar
https://api.shareai.now- Otentikasi
- Bearer API key utawa token akses OAuth sing disetujui
Pilih model embedding sing diaktifake ing ShareAI lan diidini dening kredensialmu. Model obrolan ora bisa diganti dadi model embedding. Kasedhiyan model lan pilihan sing didhukung gumantung marang panyedhiya sing dikonfigurasi.
Kirim panjalukan#
cURL
curl --fail-with-body --request POST \
"https://api.shareai.now/api/v1/embeddings" \
-H "Authorization: Bearer $SHAREAI_API_KEY" \
-H "Content-Type: application/json" \
--data '{
"model": "YOUR_EMBEDDING_MODEL",
"input": [
"How do I connect a device?",
"Where can I read my usage?"
],
"encoding_format": "float"
}'
Python
import json
import os
import urllib.request
headers = {"Authorization": "Bearer " + os.environ["SHAREAI_API_KEY"]}
headers["Content-Type"] = "application/json"
payload = {'model': 'YOUR_EMBEDDING_MODEL', 'input': ['How do I connect a device?', 'Where can I read my usage?'], 'encoding_format': 'float'}
data = json.dumps(payload).encode()
request = urllib.request.Request('https://api.shareai.now/api/v1/embeddings', data=data, headers=headers, method='POST')
with urllib.request.urlopen(request, timeout=60) as response:
print(json.load(response))
TypeScript
const url = "https://api.shareai.now/api/v1/embeddings";
const headers: Record = {
Authorization: `Bearer ${process.env.SHAREAI_API_KEY}`,
};
headers["Content-Type"] = "application/json";
const payload = {
"model": "YOUR_EMBEDDING_MODEL",
"input": [
"How do I connect a device?",
"Where can I read my usage?"
],
"encoding_format": "float"
};
const response = await fetch(url, { method: "POST", headers, body: JSON.stringify(payload) });
if (!response.ok) throw new Error(`${response.status}: ${await response.text()}`);
console.log(await response.json());
Lapangan panjalukan#
| Lapangan | Nilai |
|---|---|
model | ID model embedding sing diaktifake. |
input | String sing ora kosong utawa array nganti 128 string sing ora kosong. |
encoding_format | float utawa base64. |
dimensions | Integer opsional saka 1 nganti 65536; model sing dipilih kudu ndhukung iki. |
Maca vektor#
Waca data array lan gunakake asil saben index kanggo cocog embedding karo input. Tansah nggunakake model lan dimensi sing padha nalika embedding dokumenmu lan pitakonan telusuran. Asil uga kalebu laporan saka panyedhiya usage.
Batch ing sajroning watesan#
Teks input gabungan diwatesi nganti 256 KiB. Tanggapan sinkron lan diwatesi nganti 2 MiB, mula vektor gedhe utawa batch bisa ngluwihi wates tanggapan. Kurangi ukuran batch utawa gunakake dimensi sing luwih cilik sing didhukung. Array Token-ID ora ditampa.
Otentikasi lan kasedhiyan#
Token akses OAuth sing disetujui bisa ngganti kunci API. Panjalukan sing didanai akun mbutuhake surcharge lan rencana sing ditampa. Watesan model lan panyedhiya isih ditrapake. Yen model ora diaktifake kanggo embedding, pilih model embedding sing kasedhiya; ngganti kredensial ora bisa ngaktifake model.
Panggunaan#
Embedding nggunakake token input. Priksa rega model sadurunge mbukak batch gedhe lan gunakake Panggunaan Konsol kanggo mriksa aktivitas. Tangani validasi, otorisasi, lan kesalahan kasedhiyan sadurunge nyoba maneh.
Paling anyar dianyari Septèmber 15, 2026