Maziko a chidziwitso / Opanga mapulogalamu

Zida ndi SDKs

Chilichonse chomwe chingathe kulankhula ndi OpenAI kapena Anthropic chingathe kulankhula ndi Nymbot. M'malo ambiri, zimaphatikizapo base URL, kiyi, komanso dzina la model.

Tsambali lamasuliridwa pamakina kuti zikhale zosavuta. Chingelezi choyambirira ndi chomwe chimagwira ntchito.

Konzekerani zonse zomwe zili pansipa zikufunika API key, yomwe inapangidwa m'app's API menyu (onani Ma API keys), ndipo id ya model kuchokera ku ndandanda ya ma modelZitsanzo zikugwiritsa ntchito anthropic/claude-sonnet-5 pa balance ya Pro. nymbot/auto ndi chisankho chotsika mtengo pa kachapa wamba wa macheza osiyanasiyana, koma sangathe kugwiritsa ntchito zida zomwe Goose akufuna; chifukwa cha zimenezo, sankhani mtundu wa katalog uli ndi capabilities.tools.

Mayendetsedwe a ma coding agents monga Claude Code, Codex, Cline, Kilo Code ndi Continue ali pa tsamba lofala: ziyenero za coding.

OpenAI SDK

Makütübula odalirika a Python ndi JavaScript akugwira ntchito popanda kusintha. Point base_url at Nymbot ndipo ndipatseni kiyi yanu. Chat Completions, Responses, images, audio and embeddings zonse zimagwirizana nawo kudzera mwa iwo.

cURL

curl https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "anthropic/claude-sonnet-5", "messages": [{"role": "user", "content": "Hello"}]}'

Python

# pip install openai
import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

reply = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

JavaScript

// npm install openai
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://nymbot.ai/api/v1", apiKey: process.env.NYMBOT_API_KEY });

const reply = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);

Malo a Nymbot eni, monga plugins kuti kufufuza pa webu, pitani m'kati extra_body mu Python ndipo mwachindapita m'objekiti ya request mu JavaScript. The nymbot mtengo chinthu m'mayankho ndi reply.model_extra["nymbot"] mu Python ndipo reply.nymbot mu JavaScript. Maktabu omwe amawerenga OPENAI_BASE_URL ndi OPENAI_API_KEY zomwe zili m'malo osungira zinthu (environment variables) zitha kuhekenda ku Nymbot ndi zimenezi kokha.

Anthropic SDK

Maktabu a Anthropic amagwiritsa ntchito https://nymbot.ai/api monga URL yoyambira, popanda /v1, chifukwa amaonjezera /v1/messages iwo eni. Model iliyonse ya catalog imagwira ntchito, osati Claude okha.

cURL

curl https://nymbot.ai/api/v1/messages \
  -H "x-api-key: $NYMBOT_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-5", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}]}'

Python

# pip install anthropic
import os
import anthropic

client = anthropic.Anthropic(base_url="https://nymbot.ai/api", api_key=os.environ["NYMBOT_API_KEY"])

message = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

JavaScript

// npm install @anthropic-ai/sdk
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({ baseURL: "https://nymbot.ai/api", apiKey: process.env.NYMBOT_API_KEY });

const message = await client.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content[0].text);

Thandiza

Aider amakambirana ndi server iliyonse yomwe ikugwirizana ndi OpenAI. Sankhani base URL ndi key, ndipo ikani openai/ pamaso pa id ya model kuti Aider idziwe mtundu wa server womwe ndiwe:

Shell

export OPENAI_API_BASE=https://nymbot.ai/api/v1
export OPENAI_API_KEY=sk-nymbot-...
aider --model openai/anthropic/claude-sonnet-5

Aider akhoza kudziwitsa kuti sindikudziwa kukula kwa muخه wa model kapena mtengo wake. Chenjezo chake sichikhudza; --no-show-model-warnings amachibisa.

Open WebUI

Mu Open WebUI, tumikani Paneli la Admin, ndipo Zokonza, ndipo Malumikizano, ndipo awonjezere ma OpenAI API connection:

• URL: https://nymbot.ai/api/v1
• Kiyi: kiyi yanu ya API

Open WebUI imawerenga mndandanda wa mamodeli kuchokera ku API, choncho mu chat model iliyonse imafika pa osankhula. Pogwiritsa ntchito mu Docker, zimenezi zitha kukhazikitsidwa pogwiritsa ntchito environment variables OPENAI_API_BASE_URL ndi OPENAI_API_KEY.

Open WebUI imasunga zokambirana zanu pa seva yake yodziwika. Nymbot sikusunga izo, koma Open WebUI imasunga, kulikonse kumene mukugwiritsa ntchito.

Nkhuku yandala

Tamangani goose configure, sankhani Konza Opereka, sankhani OpenAI, ndipo ipatseni ma value awa akafunsa. Zomwezi zitha kukhazikitsidwa mwa environment:

Shell

export GOOSE_PROVIDER=openai
export OPENAI_HOST=https://nymbot.ai/api
export OPENAI_BASE_PATH=v1/chat/completions
export OPENAI_API_KEY=sk-nymbot-...
export GOOSE_MODEL=anthropic/claude-sonnet-5
goose session

Goose amagwiritsa ntchito zida pa chilichonse chomwe chimachitika, choncho sankhani mtundu wa model uli ndi capabilities.tools mu ndandanda wa mamodeli; nymbot/auto akana zida.

HTTP yosavuta

Palibe chomwe chofunika SDK. Endpoint iliyonse ndi JSON kudzera ku HTTPS, kupatula kumatulira mafayilo, omwe ndi multipart forms. Chinenero kapena chida chilichonse chomwe chingathe kupanga HTTP request chingagwiritse ntchito API iyi:

• Tumiza kiyi monga Authorization: Bearer sk-nymbot-….
• Tumizani ma JSON bodies ndi Content-Type: application/json.
• Kuti mutumize mwachindunji,werengani yankho ngati server-sent events; ndi cURL, onjezani -N chonso imazitula pamene zikufika.
• Werengani mtengo kuchokera ku X-Nymbot-Cost-Sats mutu, ndipo sungani X-Request-Id mutu ngati mungafune kufunsa za pempho.

cURL

curl -i https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nymbot/auto", "messages": [{"role": "user", "content": "Hello"}]}'

Python

import os
import requests

res = requests.post(
    "https://nymbot.ai/api/v1/chat/completions",
    headers={"Authorization": "Bearer " + os.environ["NYMBOT_API_KEY"]},
    json={"model": "nymbot/auto", "messages": [{"role": "user", "content": "Hello"}]},
)
print(res.headers["X-Nymbot-Cost-Sats"], res.headers["X-Request-Id"])
print(res.json()["choices"][0]["message"]["content"])

JavaScript

const res = await fetch("https://nymbot.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.NYMBOT_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ model: "nymbot/auto", messages: [{ role: "user", content: "Hello" }] }),
});
console.log(res.headers.get("X-Nymbot-Cost-Sats"), res.headers.get("X-Request-Id"));
console.log((await res.json()).choices[0].message.content);