undefined - Protocol API Reference

POSThttps://api.usemeru.com/refine/v2/predict

Text/Code Completion

A prediction is how you run an inference request on a model that is supported by Meru. Information about parameters passed into OpenAI's models is taken directly from OpenAI's website. Use this POST command to complete a chunk of natural language or code.

Authentication

Name
x-api-key
Type
string
Description
Your Meru API Key

Required Attributes

Name
model_id
Type
string
Description
Unique identifier for the other contact in the conversation. You can find all the model_ids we support in the Models section on the right side. Copy and paste the identifier exactly how it is listed in the table.
Name
prompt
Type
string
Description
This is your prompt that will be used to generate an image or additional text, based on the model you have chosen.

Optional Attributes

Name
suffix
Type
string
Description
The suffix that comes after a completion of inserted text.
Name
max_tokens
Type
integer
Description
The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).
Name
temperature
Type
number
Description
What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend altering this or top_p but not both.
Name
top_p
Type
number
Description
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
Name
n
Type
integer
Description
How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.
Name
logprobs
Type
integer
Description
Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response. The maximum value for logprobs is 5.
Name
stop
Type
string
Description
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
Name
echo
Type
boolean
Description
Echo back the prompt in addition to the completion
Name
presence_penalty
Type
number
Description
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
Name
frequency_penalty
Type
number
Description
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
Name
best_of
Type
integer
Description
Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. When used with n, best_of controls the number of candidate completions and n specifies how many to return – best_of must be greater than n.

Request

POST

refine/v2/predict

curl https://api.usemeru.com/refine/v2/predict \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: ${API Key}' \
  -d '{
    "model_id": "text-davinci-003",
    "inputs": {
            "prompt": "how are you doing?"
    }
  }'

Response

    {
      "err_code": 0, 
      "id": JOB_ID, 
      "outputs": {
        "object": "text_completion", 
        "choices": [
          {
            "text": "\n\nI'm doing well, thank you for asking. How are you?", 
            "index": 0, 
            "logprobs": null, 
            "finish_reason": 
            "length"
          }
        ], 
        "usage": {
          "prompt_tokens": 5, 
          "completion_tokens": 16, 
          "total_tokens": 21
          }
        }, 
        "cost": 0.000378
    }

POSThttps://api.usemeru.com/refine/v2/predict/{job_id}

Text/Code Editing

Make a POST request to complete a chunk of code using one of the Codex models. Information about parameters passed into codex models is taken directly from OpenAI's website.

Authentication

Name
x-api-key
Type
string
Description
Your Meru API Key

Required Attributes

Name
model_id
Type
string
Description
Unique identifier for the other contact in the conversation. You can find all the model_ids we support in the Models section on the right side. Copy and paste the identifier exactly how it is listed in the table.
Name
instruction
Type
string
Description
The instruction that tells the model how to edit the prompt.

Optional Attributes

Name
n
Type
integer
Description
(Defaults to 1) How many edits to generate for the input and instruction.
Name
input
Type
string
Description
(Defaults to ") The input text to use as a starting point for the edit.
Name
temperature
Type
number
Description
(Defaults to 1) What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend altering this or top_p but not both.
Name
top_p
Type
number
Description
(Defaults to 1) An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

Request

POST

refine/v2/predict/

curl https://api.usemeru.com/refine/v2/predict \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: ${API Key}' \
  -d '{
    "model_id": "text-davinci-edit-001",
    "inputs": {
        "input":"What day of the wek is it?",
        "instruction":"Fix the spelling mistakes"
    }
  }'

Response

{
  "err_code": 0, 
  "id": JOB_ID, 
  "outputs": {
    "object": "edit", 
    "choices": [
      {
        "text": "What day of the week is it?\n",
        "index": 0
      }
    ], 
    "usage": {
      "prompt_tokens": 25,
      "completion_tokens": 28,
      "total_tokens": 53
    }
  },
"cost": 0.000954
}

GEThttps://api.usemeru.com/refine/v2/predict/{job_id}

Retrieve Completion or Edit

Make a GET request to retrieve a previously completed prediction.

Authentication

Name
x-api-key
Type
string
Description
Your Meru API Key

Request

GET

refine/v2/predict/{job_id}

curl https://api.usemeru.com/refine/v2/predict/{job_id} \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: ${API Key}'

Response

{
  "err_code": 0, 
  "id": JOB_ID, 
  "outputs": {
    "object": "edit", 
    "choices": [
      {
        "text": "What day of the week is it?\n",
        "index": 0
      }
    ], 
    "usage": {
      "prompt_tokens": 25,
      "completion_tokens": 28,
      "total_tokens": 53
    }
  },
"cost": 0.000954
}

POSThttps://api.usemeru.com/refine/v2/predict/

Generate Image

Submit a POST request to generate an image with Stable Diffusion. Does not return image (must retrieve image with GET request).

Authentication

Name
x-api-key
Type
string
Description
Your Meru API Key

Required Attributes

Name
prompt
Type
string
Description
Prompt for image generation.

Optional Attributes

Name
num_samples
Type
integer
Description
(Default: 1). Number of samples (seperate images) to generate. Maximum is 8.
Name
guidance_scale
Type
number
Description
(Default: 7.5). Higher values place more weight on the prompt.
Name
seed
Type
integer
Description
(Default: 42). Seed for generation. Stick to a static seed to see similar results across inference runs. To randomize, set seed to -1.
Name
num_inference_steps
Type
integer
Description
(Default: 50) Number of steps to run inference for. We don't recommend going beyond 100 steps.
Name
height
Type
integer
Description
(Default: 512) Image height in pixels. Note: Total image size (width multiplied by height) must be less than 786432 pixels.
Name
width
Type
integer
Description
(Default: 512) Image width in pixels. Note: Total image size (width multiplied by height) must be less than 786432 pixels.

Request

POST

refine/v2/predict/

curl https://api.usemeru.com/refine/v2/predict \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: ${API_KEY}' \
  -d '{
    "model_id": "stability-diffusion-v1-5",
    "inputs": {
        "prompt" : "A picture of a cheescake with happy birthday written on it"
    }
  }'

Response

  {
    "err_code": 0,
    "id": JOB_ID, 
    "status_code": 1
  }

GEThttps://api.usemeru.com/refine/v2/predict/{job_id}

Retrieve Image

Make a GET request to retrieve a set of images from a completed generation job.

Authentication

Name
x-api-key
Type
string
Description
Your Meru API Key

Request

GET

refine/v2/predict/{job_id}

curl https://api.usemeru.com/refine/v2/predict/{job_id} \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: ${API Key}'

Response

{
  "err_code": 0, 
  "id": JOB_ID, 
  "outputs": {
  "infer_urls_upscaled": {
    [LIST_OF_IMAGE_URLS]
    }, 
  "image_urls":{
    [LIST_OF_IMAGE_URLS]
    },
  "cost": "0.005152512450730734"
}