OpenAI codex api: Quickstart med Python

Installer den officielle SDK

Brug det officielle SDK for at sikre kompatibilitet med vores openai proxy API. Denne tilgang fungerer med ethvert standardbibliotek, der understøtter OpenAI-protokollen.

• Installer pakken via din foretrukne pakkehåndtering.
• Verificér installationen ved at importere biblioteket.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicodexapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Indstil din Base URL og nøgle

Peg din klient mod vores openai gateway endpoint for at få adgang til den ubegrænsede AI-model. Erstat standard base URL med vores specifikke endpoint.

• Indstil API-nøglen i dine miljøvariabler.
• Konfigurer base-URL'en til https://api.openaicodexapi.com/v1.

Denne opsætning sikrer, at dine anmodninger dirigeres korrekt til vores servere uden at modificere din eksisterende kodestruktur.

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

Send din første forespørgsel

Send en simpel text completion for at teste forbindelsen. Brug model-ID uncensored til anmodningen.

• Definer meddeholdelsens indhold.
• Udfør anmodningen.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicodexapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Svaret returnerer den genererede tekst direkte.

Aktiver Streaming og JSON-tilstand

Stream-svar for lavere latens eller aktiver JSON-tilstand til strukturerede data. Indstil stream=true for real-time token levering.

• Brug response_format til JSON-output.
• Håndter chunks i din kode.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

Streaming hjælper dig med hurtigt at vise delvise resultater.

Håndter tools og function calling

Definer værktøjer i din request for at aktivere function calling. Angiv værktogsdefinitionerne, og lad modellen afgøre, hvornår de skal bruges.

• Definer funktions-skemaet.
• Parser værktjskaldene i svaret.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicodexapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Denne funktion muliggør integration med eksterne systemer.

Begrænsninger, fejl og kontekstvindue

Overvåg dit forbrug for at undgå rate limits eller fejl. Context-vinduet understøtter i alt 100.000 tokens.

• Håndter 401-fejl for ugyldige nøgler.
• Håndter 402-fejl for utilstrækkelig kredit.
• Håndter 429-fejl for hastighedsbegrænsninger.

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicodexapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)