Inference API
Generate
Generate tokens and wait for completion
POST
/
generate
Copy
Ask AI
curl --request POST \
--url https://serving.app.predibase.com/tenant_id/deployments/v2/llms/deployment_name/generate \
--header 'Content-Type: application/json' \
--data '{
"inputs": "My name is Olivier and I",
"parameters": {
"best_of": 1,
"decoder_input_details": "false",
"details": "false",
"do_sample": true,
"max_new_tokens": "null",
"ignore_eos_token": true,
"repetition_penalty": 1.03,
"return_full_text": false,
"seed": "null",
"stop": [
"photographer"
],
"temperature": 0.5,
"top_k": 10,
"top_p": 0.95,
"truncate": "null",
"typical_p": 0.95,
"watermark": true,
"schema": "{\"type\": \"string\", \"title\": \"response\"}",
"adapter_id": "<string>",
"adapter_source": "<string>",
"merged_adapters": {
"ids": [
"adapter1",
"adapter2"
],
"weights": [
0.5,
0.5
],
"merge_strategy": "ties",
"density": 0.5,
"majority_sign_method": "total"
},
"api_token": "<string>",
"apply_chat_template": true
}
}'
Copy
Ask AI
{
"details": {
"best_of_sequences": [
{
"finish_reason": "length",
"generated_text": "test",
"generated_tokens": 1,
"skipped_tokens": 1,
"prefill": [
{
"id": 0,
"logprob": -0.34,
"text": "test"
}
],
"seed": 42,
"tokens": [
{
"id": 0,
"logprob": -0.34,
"special": "false",
"text": "test",
"skipped": "true"
}
]
}
],
"finish_reason": "length",
"prompt_tokens": 1,
"generated_tokens": 1,
"prefill": [
{
"id": 0,
"logprob": -0.34,
"text": "test"
}
],
"seed": 42,
"tokens": [
{
"id": 0,
"logprob": -0.34,
"special": "false",
"text": "test",
"skipped": "true"
}
]
},
"generated_text": "test"
}
Body
application/json
Response
200
application/json
Generated Text
The response is of type object
.
Copy
Ask AI
curl --request POST \
--url https://serving.app.predibase.com/tenant_id/deployments/v2/llms/deployment_name/generate \
--header 'Content-Type: application/json' \
--data '{
"inputs": "My name is Olivier and I",
"parameters": {
"best_of": 1,
"decoder_input_details": "false",
"details": "false",
"do_sample": true,
"max_new_tokens": "null",
"ignore_eos_token": true,
"repetition_penalty": 1.03,
"return_full_text": false,
"seed": "null",
"stop": [
"photographer"
],
"temperature": 0.5,
"top_k": 10,
"top_p": 0.95,
"truncate": "null",
"typical_p": 0.95,
"watermark": true,
"schema": "{\"type\": \"string\", \"title\": \"response\"}",
"adapter_id": "<string>",
"adapter_source": "<string>",
"merged_adapters": {
"ids": [
"adapter1",
"adapter2"
],
"weights": [
0.5,
0.5
],
"merge_strategy": "ties",
"density": 0.5,
"majority_sign_method": "total"
},
"api_token": "<string>",
"apply_chat_template": true
}
}'
Copy
Ask AI
{
"details": {
"best_of_sequences": [
{
"finish_reason": "length",
"generated_text": "test",
"generated_tokens": 1,
"skipped_tokens": 1,
"prefill": [
{
"id": 0,
"logprob": -0.34,
"text": "test"
}
],
"seed": 42,
"tokens": [
{
"id": 0,
"logprob": -0.34,
"special": "false",
"text": "test",
"skipped": "true"
}
]
}
],
"finish_reason": "length",
"prompt_tokens": 1,
"generated_tokens": 1,
"prefill": [
{
"id": 0,
"logprob": -0.34,
"text": "test"
}
],
"seed": 42,
"tokens": [
{
"id": 0,
"logprob": -0.34,
"special": "false",
"text": "test",
"skipped": "true"
}
]
},
"generated_text": "test"
}
Assistant
Responses are generated using AI and may contain mistakes.