AI Developer - Postman example
On this page you can find an example on how to use the Ozeki HTTP API to communicate with an AI model. The example is based on submitting a request using the Postman HTTP API tester tool. Note, that if you use the API key, you don't need to use the username/password. The model we use is the LLama3 Nemotron 70b modelr. When you try this method, please be patient. The AI server can take a long time to respond.
Example request
The following webpage contains information on how you can setup an HTTP API user in your own system:
You can use the following tool to test the HTTP API functionality
API access
To access the test API you can use the following credentials. Note, that these are subject to change, and it is best to setup an HTTP API user on your own system.
Host | https://www1.ozeki.hu:9510/api? |
Host | http://www1.ozeki.hu:9511/api? |
Username | ozekai |
Password | apipass |
API key | eyJhbGciOiJSUzM4NCIsImNpZCI6Im96ZWtpYWlAbG9jYWxob3N0In0.eyJraWQiOiJSUVhBUFZXVlVOVEdSSlpDT0VUWUxTTExERE1OWFVWTSIsImlhdCI6MTczNTk3Mzk0Nn0.TPiwtfIHtfXcKCnCuqNCfxrFhNbcS8OJRQpCH4dh_EMIVGyLAXTHGpO3HyjO2EDCUHYrgGx3GplKPZ2FaLjodvQ-c6jEDDNeMTwSK3t10LApBuiFhMpWm8b5qgGg_-nDt9pBR7I87ocXgzwiSE8of0FbpJIhERrq1RnC2viqurNsrkOKyyJ97T5hHt_WxIImpBc1AT04HyYBAKipIkG-_HJCbif4VHX8Rj6-BhZcXs8tFaHaTufSWaQO3sD9wcGEccyHeRKqpTt5P2sy5WfZajqAS019rflNhvjIElKJ2Mow-O9Fp4YNoa4-quQprGaBB9ZiEhHn7CuIhvL_ogGNFQ |
Model | Nemotron-70B |
Hint: You must create your own credentials on your own AI server to work.
AI Server models
The AI Server currently has the following models installed:
HTTP request
To do an example request configure the following paramters in the PostMan HTTP API tester tool.
Example request
POST /api?command=chatgpt HTTP/1.1 Content-Type: application/json Authorization: Bearer eyJhbGciOiJSUzM4NCIsImNpZCI6Im96ZWtpYWlAbG9jYWxob3N0In0.eyJraWQiOiJSUVhBUFZXVlVOVEdSSlpDT0VUWUxTTExERE1OWFVWTSIsImlhdCI6MTczNTk3Mzk0Nn0.TPiwtfIHtfXcKCnCuqNCfxrFhNbcS8OJRQpCH4dh_EMIVGyLAXTHGpO3HyjO2EDCUHYrgGx3GplKPZ2FaLjodvQ-c6jEDDNeMTwSK3t10LApBuiFhMpWm8b5qgGg_-nDt9pBR7I87ocXgzwiSE8of0FbpJIhERrq1RnC2viqurNsrkOKyyJ97T5hHt_WxIImpBc1AT04HyYBAKipIkG-_HJCbif4VHX8Rj6-BhZcXs8tFaHaTufSWaQO3sD9wcGEccyHeRKqpTt5P2sy5WfZajqAS019rflNhvjIElKJ2Mow-O9Fp4YNoa4-quQprGaBB9ZiEhHn7CuIhvL_ogGNFQ User-Agent: PostmanRuntime/7.41.1 Accept: */* Postman-Token: e4ffb35d-d7ef-4935-adb1-16d4f7b61441 Host: www1.ozeki.hu:9511 Accept-Encoding: gzip, deflate, br Connection: keep-alive Content-Length: 844 { "model": "Nemotron-70B", "messages": [ { "role": "system", "content": "Transcript of a conversation between the User and an Assistant. Assistant is a friendly, reliable, and highly knowledgeable assistant, known for being helpful, empathetic, and honest. Assistant consistently delivers prompt, clear, and accurate responses, excelling in writing and problem-solving, ensuring the User's requests are addressed with precision and care!" }, { "role": "user", "content": "Hello" }, { "role": "assistant", "content": "How may I help you today?" }, { "role": "user", "content": "Where is London?" } ], "temperature": 0.7, "max_completion_tokens": 100 }
Example response
HTTP/1.1 200 OK Transfer-Encoding: chunked Content-Type: application/json; charset=utf8 Last-Modified: Sun, 29 Dec 2024 07:27:03 GMT Server: 10/10.3.163 Microsoft-HTTPAPI/2.0 User-Agent: OZEKI 10.3.163 (www.ozeki.hu) Access-Control-Allow-Origin: * Date: Sat, 04 Jan 2025 06:54:20 GMT { "id": "chatcmpl-TVSWKIRVGZRJLLUPFQWMZRDVNSXZA", "object": "chat.completion", "created": 1735974466, "model": "Nemotron-70B", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "**Location Alert!**\nLondon is located in:\n* **Country:** England\n* **Region:** South East England\n* **Geographic Coordinates:** 51.5074° N, 0.1278° W\n\nTo give you a better idea, London is situated:\n* About 45 miles (72 km) northwest of the English Channel\n* Along the River Thames, which flows through the heart of the city\n* In the southeastern part of England, roughly equ", "refusal": null }, "logprobs": null, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0, "completion_tokens_details": { "reasoning_tokens": 0 } }, "system_fingerprint": "fp_f85bea6784" }
More information
- Example HTTP API request using Postman for Ozeki Chat GPT API
- Example HTTP API request using Curl for Ozeki Chat GPT API
- HTTP tester tools
- AI prompt
- AI code generation VS code plugin