GenAI API

A GenAI API is an interactive and user-friendly platform to selects models,configure parameters and observe the results, designed for experimenting with machine learning AI models. It provides a space where users, including data scientists, researchers, and developers, can explore, test, and Open Source machine learning models without the need for extensive coding or infrastructure setup.

List of Models

To get the list of Models, send a GET request to the GenAI Endpoint

https://api.e2enetworks.com/myaccount/api/v1/gpu/teams/{{team_id}}/projects/{{project_id}}/model_playground/?apikey={{tapi_key}}

import requests

url = "https://api.e2enetworks.com/myaccount/api/v1/gpu/teams/{{team_id}}/projects/{{project_id}}/model_playground/?apikey={{tapi_key}}"

payload={}
headers = {
'Authorization': 'Bearer {{Token}}',
'Content-Type': 'application/json',
}

response = requests.request("GET", url, headers=headers, data=payload)

print(response.text)

Content-Type: application/json
Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAi...

Stable Diffussion response

To get the Stable Diffusion response with provided request, send a POST request to the Finetuning Endpoint

https://infer.e2enetworks.net/project/p-{{project_id}}/v1/stable-diffusion-2-1/infer?apikey={{tapi_key}}

import requests
import json

url = "https://infer.e2enetworks.net/project/p-{{project_id}}/v1/stable-diffusion-2-1/infer?apikey={{tapi_key}}"

payload = json.dumps({
"inputs": [
    {
    "name": "prompt",
    "shape": [
        1,
        1
    ],
    "datatype": "BYTES",
    "data": [
        "A photo of an astronaut riding a horse on mars"
    ]
    },
    {
    "name": "height",
    "shape": [
        1,
        1
    ],
    "datatype": "UINT16",
    "data": [
        768
    ]
    },
    {
    "name": "width",
    "shape": [
        1,
        1
    ],
    "datatype": "UINT16",
    "data": [
        768
    ]
    },
    {
    "name": "num_inference_steps",
    "shape": [
        1,
        1
    ],
    "datatype": "UINT16",
    "data": [
        50
    ]
    },
    {
    "name": "guidance_scale",
    "shape": [
        1,
        1
    ],
    "datatype": "FP32",
    "data": [
        7.5
    ]
    },
    {
    "name": "guidance_rescale",
    "shape": [
        1,
        1
    ],
    "datatype": "FP32",
    "data": [
        0.7
    ]
    }
]
})
headers = {
    'Authorization': 'Bearer {{Token}}',
    'Content-Type': 'application/json',
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

Content-Type: application/json
Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAi...

{
"inputs": [
    {
        "name": "prompt",
        "shape": [
            1,
            1
        ],
        "datatype": "BYTES",
        "data": [
            "A photo of an astronaut riding a horse on mars"
        ]
    },
    {
        "name": "height",
        "shape": [
            1,
            1
        ],
        "datatype": "UINT16",
        "data": [
            768
        ]
    },
    {
        "name": "width",
        "shape": [
            1,
            1
        ],
        "datatype": "UINT16",
        "data": [
            768
        ]
    },
    {
        "name": "num_inference_steps",
        "shape": [
            1,
            1
        ],
        "datatype": "UINT16",
        "data": [
            50
        ]
    },
    {
        "name": "guidance_scale",
        "shape": [
            1,
            1
        ],
        "datatype": "FP32",
        "data": [
            7.5
        ]
    },
    {
        "name": "guidance_rescale",
        "shape": [
            1,
            1
        ],
        "datatype": "FP32",
        "data": [
            0.7
        ]
    }
]
}

WhisperLarge V3 Response

To get the WhisperLarge V3 Response with provided request, send a POST request to the Finetuning Endpoint

https://infer.e2enetworks.net/project/p-{{project_id}}/v1/whisper-large-v3/infer?apikey={{tapi_key}}

import requests
import json

url = "https://infer.e2enetworks.net/project/p-{{project_id}}/v1/whisper-large-v3/infer?apikey={{tapi_key}}"

payload = json.dumps({
"inputs": [
    {
    "name": "input",
    "shape": [
        1
    ],
    "datatype": "BYTES",
    "data": [
        "{{path"
    ]
    },
    {
    "name": "language",
    "shape": [
        1
    ],
    "datatype": "BYTES",
    "data": [
        "English"
    ]
    },
    {
    "name": "task",
    "shape": [
        1
    ],
    "datatype": "BYTES",
    "data": [
        "transcribe"
    ]
    },
    {
    "name": "max_new_tokens",
    "shape": [
        1
    ],
    "datatype": "INT32",
    "data": [
        400
    ]
    },
    {
    "name": "return_timestamps",
    "shape": [
        1
    ],
    "datatype": "BYTES",
    "data": [
        "none"
    ]
    }
]
})
headers = {
    'Authorization': 'Bearer {{Token}}',
    'Content-Type': 'application/json',
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

Content-Type: application/json
Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAi...

{
    "inputs": [
    {
        "name": "input",
        "shape": [
            1
        ],
        "datatype": "BYTES",
        "data": [
            "/mnt/data/3005-1720514090-recording.wav"
        ]
    },
    {
        "name": "language",
        "shape": [
            1
        ],
        "datatype": "BYTES",
        "data": [
            "English"
        ]
    },
    {
        "name": "task",
        "shape": [
            1
        ],
        "datatype": "BYTES",
        "data": [
            "transcribe"
        ]
    },
    {
        "name": "max_new_tokens",
        "shape": [
            1
        ],
        "datatype": "INT32",
        "data": [
            400
        ]
    },
    {
        "name": "return_timestamps",
        "shape": [
            1
        ],
        "datatype": "BYTES",
        "data": [
            "none"
        ]
    }
    ]
}

Llama2 Response

To get the Llama2 Response with provided request, send a POST request to the Finetuning Endpoint

https://infer.e2enetworks.net/project/p-{{project_id}}/genai/v1/chat/completions

import requests
import json

url = "https://infer.e2enetworks.net/project/p-{{project_id}}/genai/v1/chat/completions"

payload = json.dumps({
"temperature": 0.5,
"max_tokens": 1024,
"top_p": 1,
"frequency_penalty": 0,
"seed": 999,
"presence_penalty": 1,
"stream": True,
"model": "llama-2-13b-chat",
"messages": [
    {
    "role": "user",
    "content": "Can you write a poem about open source machine learning?"
    }
]
})
headers = {
    'Authorization': 'Bearer {{Token}}',
    'Content-Type': 'application/json',
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

Content-Type: application/json
Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAi...

{
"temperature": 0.5,
"max_tokens": 1024,
"top_p": 1,
"frequency_penalty": 0,
"seed": 999,
"presence_penalty": 1,
"stream": true,
"model": "llama-2-13b-chat",
"messages": [
    {
    "role": "user",
    "content": "Can you write a poem about open source machine learning?"
    }
]
}

Llama3 Response

To get the Llama3 Response with provided request, send a POST request to the Finetuning Endpoint

https://infer.e2enetworks.net/project/p-{{project_id}}/genai/v1/chat/completions

import requests
import json

url = "https://infer.e2enetworks.net/project/p-{{project_id}}/genai/v1/chat/completions"

payload = json.dumps({
"temperature": 0.5,
"max_tokens": 1024,
"top_p": 1,
"frequency_penalty": 0,
"seed": 999,
"presence_penalty": 1,
"stream": True,
"model": "llama-3-8b-instruct",
"messages": [
    {
    "role": "user",
    "content": "Can you write a poem about open source machine learning?"
    }
]
})
headers = {
    'Authorization': 'Bearer {{Token}}',
    'Content-Type': 'application/json',
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

Content-Type: application/json
Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAi...

{
"temperature": 0.5,
"max_tokens": 1024,
"top_p": 1,
"frequency_penalty": 0,
"seed": 999,
"presence_penalty": 1,
"stream": true,
"model": "llama-3-8b-instruct",
"messages": [
    {
    "role": "user",
    "content": "Can you write a poem about open source machine learning?"
    }
]
}

Vector Embeddings Response

To get the Vector Embeddings Response with provided request, send a POST request to the Finetuning Endpoint

https://infer.e2enetworks.net/project/p-{{project_id}}/genai/v1/embeddings

import requests
import json

url = "https://infer.e2enetworks.net/project/p-{{project_id}}/genai/v1/embeddings"

payload = "{\n  \"model\": \"e5-mistral-7b-instruct\",\n  \"input\": \"Generate your text embeddings here\",\n  \"encoding_format\": \"float\",\n  \"dimensions\": 4096 //only dimensions == 4096 is supported\n}"
headers = {
    'Authorization': 'Bearer {{Token}}',
    'Content-Type': 'application/json',
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

Content-Type: application/json
Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAi...

{
"model": "e5-mistral-7b-instruct",
"input": "Generate your text embeddings here",
"encoding_format": "float",
"dimensions": 4096 //only dimensions == 4096 is supported
}