Streaming SSE
F'din il-paġna
Risposti f’ħin reali
Fil-modalità normali, tistenna sakemm il-mudell jispiċċa jiġġenera r-risposta sħiħa qabel ma tirċieviha. Bis-streaming SSE (Server-Sent Events), it-tokens jaslu hekk kif jiġu ġġenerati. Dan huwa essenzjali għal interfaċċi konversazzjonali fejn l-utenti jridu jaraw ir-risposta tidher progressivament.
Attiva s-streaming
Żid "stream": true mat-talba tiegħek:
curl https://api.x.ai/v1/responses \
-H "Authorization: Bearer $XAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-4.20-0309-reasoning",
"input": "Write a poem about programming.",
"stream": true
}'
Ir-risposta tasal bħala fluss SSE:
data: {"type": "response.created", "response": {...}}
data: {"type": "response.output_item.added", ...}
data: {"type": "response.content_part.added", ...}
data: {"type": "response.output_text.delta", "delta": "La "}
data: {"type": "response.output_text.delta", "delta": "programmation "}
data: {"type": "response.output_text.delta", "delta": "est "}
...
data: {"type": "response.completed", "response": {...}}
Tipi ta’ avvenimenti
| Avveniment | Deskrizzjoni |
|---|---|
response.created | Tibda l-ġenerazzjoni |
response.output_item.added | Element ġdid fl-output |
response.content_part.added | Parti ġdida tal-kontenut |
response.output_text.delta | Framment ta’ test (l-aktar frekwenti) |
response.output_text.done | Test sħiħ ta’ element |
response.completed | Risposta finalizzata bl-użu |
response.failed | Żball waqt il-ġenerazzjoni |
Streaming f’Python
stream = client.responses.create(
model="grok-4.20-0309-reasoning",
input="Explain how a compiler works.",
stream=True
)
full_text = ""
for event in stream:
if event.type == "response.output_text.delta":
print(event.delta, end="", flush=True)
full_text += event.delta
elif event.type == "response.completed":
usage = event.response.usage
print(f"\n\nTokens: {usage.total_tokens}")
print(f"Cost: {usage.cost_in_nano_usd / 1e9:.6f} USD")
flush=True tifforza l-wiri immedjat ta’ kull framment.
Streaming bl-għodod
Meta l-mudell juża għodod fil-modalità streaming, tirċievi avvenimenti addizzjonali:
data: {"type": "response.output_item.added", "item": {"type": "web_search_call"}}
data: {"type": "response.web_search_call.in_progress", ...}
data: {"type": "response.web_search_call.completed", ...}
data: {"type": "response.output_text.delta", "delta": "Selon les résultats..."}
Għal sejħiet ta’ funzjonijiet mill-klijent, tirċievi l-argumenti progressivament:
data: {"type": "response.function_call.arguments.delta", "delta": "{\"city\""}
data: {"type": "response.function_call.arguments.delta", "delta": ": \"Paris\"}"}
data: {"type": "response.function_call.arguments.done", ...}
Integrazzjoni fil-Frontend
Għal applikazzjoni web, ibgħat il-fluss SSE lill-browser permezz ta’ endpoint tas-server:
const response = await fetch('/api/chat', {
method: 'POST',
body: JSON.stringify({ message: userInput })
});
const reader = response.body.getReader();
const decoder = new TextDecoder();
while (true) {
const { done, value } = await reader.read();
if (done) break;
const text = decoder.decode(value);
outputElement.textContent += text;
}
Streaming u fatturazzjoni
Is-streaming ma jbiddilx il-fatturazzjoni. L-ispiża hija identika kemm jekk attivata kif ukoll le—biss il-modalità ta’ konsinja tinbidel. L-oġġett sħiħ usage huwa disponibbli fl-avveniment response.completed.
Punti Ewlenin
stream: truejattiva s-streaming SSE—it-tokens jaslu hekk kif jiġu ġġenerati- L-avveniment
response.output_text.deltafih kull framment ta’ test - L-avveniment
response.completedfih ir-risposta finali bil-metadejta tal-użu - Is-streaming jaħdem mal-għodod (web_search, funzjonijiet)
- L-ispiża hija identika bi streaming jew mingħajru