Generate text completions using the selected Large Language Model (LLM).
The request body for this endpoint is structured to generate text completions based on a given prompt and model selection. The response will be a Completion Object.
Pass the config parameters for the request in the headers as defined here.
Portkey automatically transforms the parameters for LLMs other than OpenAI. If some parameters don't exist in the other LLMs, they will be dropped.
SDK Usage
The completions.create method in the Portkey SDK allows you to generate text completions using various LLMs. This method provides a straightforward interface for requesting text completions similar to the OpenAI API.
# with only request paramsportkey.completions.create(requestParams);# with request and config paramsportkey.with_options(configParams).completions.create(requestParams);
requestParams (Object): Parameters for the completion request. These parameters should include the prompt and model, and are transformed automatically by Portkey for LLMs other than OpenAI. Unsupported parameters for other LLMs will be dropped.
configParams (Object): Additional configuration options for the request. This is an optional parameter that can include custom config options for this specific request. These will override the configs set in the Portkey Client.
Example Usage
import Portkey from'portkey-ai';// Initialize the Portkey clientconstportkey=newPortkey({ apiKey:"PORTKEY_API_KEY",// Replace with your Portkey API key virtualKey:"VIRTUAL_KEY"// Optional: For virtual key management});// Generate a text completionasyncfunctiongetTextCompletion() {constcompletion=awaitportkey.completions.create({ prompt:"Say this is a test", model:"gpt-3.5-turbo-instruct", });console.log(completion);}awaitgetTextCompletion();
// Generate a streaming text completionasyncfunctiongetTextCompletionStream(){constcompletionStream=awaitportkey.completions.create({ prompt:"Continuously stream this test", model:"gpt-3.5-turbo-instruct", stream:true });forawait (constchunkof completionStream) {console.log(chunk.content); }}awaitgetTextCompletionStream();
// Generate a text completion with config paramsasyncfunctiongetTextCompletionWithConfig() {constcompletion=awaitportkey.completions.create({ prompt:"Say this is a test with specific config", model:"gpt-3.5-turbo-instruct", }, {config:"custom-config-123"});console.log(completion);}awaitgetTextCompletionWithConfig();
from portkey_ai import Portkey# Initialize the Portkey clientportkey =Portkey( api_key="PORTKEY_API_KEY", # Replace with your Portkey API key virtual_key="VIRTUAL_KEY"# Optional: For virtual key management)# Generate a text completiondefget_text_completion(): completion = portkey.completions.create( prompt="Say this is a test", model="gpt-3.5-turbo-instruct" )print(completion)get_text_completion()
# Example with config parametersdefget_chat_completion_with_config(): completion = portkey.with_options({'config': 'sample-7g5tr4'}).completions.create( messages=[{'role': 'user', 'content': 'Say this is a test'}], model='gpt-3.5-turbo-instruct' )print(completion)get_chat_completion_with_config()
# Generate a streaming chat completionasyncdefget_chat_completion_stream(): completion_stream = portkey.completions.create( messages=[{'role': 'user', 'content': 'Say this is a test'}], model='gpt-3.5-turbo-instruct', stream=True })for chunk in completion:print(chunk.choices[0].delta)awaitget_chat_completion_stream()
REST API Example
In REST calls, x-portkey-api-key is a compulsory header, it can be paired with the following options for sending provider details:
x-portkey-provider & Authorization (or similar auth headers)
The response will conform to the Text Completions Object schema from the Portkey API, typically including the generated text based on the prompt and the selected model.
Creates a completion for the provided prompt and parameters.
POSThttps://api.portkey.ai/v1/completions
Body
model*any of
ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.
prompt*nullable one of
The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.
best_ofnullable integer
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.
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.
echonullable boolean
Echo back the prompt in addition to the completion
frequency_penaltynullable number
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.
Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.
As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.
logprobsnullable integer
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.
max_tokensnullable integer
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. Example Python code for counting tokens.
nnullable integer
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.
presence_penaltynullable number
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.
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.
stopnullable one of
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
streamnullable boolean
Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.
suffixnullable string
The suffix that comes after a completion of inserted text.
temperaturenullable number
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or top_p but not both.
top_pnullable number
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.
userstring
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
Response
OK
Body
id*string
A unique identifier for the completion.
choices*array of object
The list of completion choices the model generated for the input prompt.
created*integer
The Unix timestamp (in seconds) of when the completion was created.
model*string
The model used for completion.
system_fingerprintstring
This fingerprint represents the backend configuration that the model runs with.
Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.
object*enum
The object type, which is always "text_completion"
text_completion
usageCompletionUsage (object)
Usage statistics for the completion request.
Request
constresponse=awaitfetch('https://api.portkey.ai/v1/completions', { method:'POST', headers: {"Content-Type":"application/json" }, body:JSON.stringify({"model":"text","prompt":"This is a test." }),});constdata=awaitresponse.json();