Batch | Parasail

Introduction to Parasail's Batch Processing Library

Parasail's batch processing engine is a straightforward and inexpensive way to process thousands or millions of LLM inferences. Batch inferencing is easy: create an input file, start a batch job, wait for it to finish, then download the output.

Getting Started with the Parasail Batch Helper Library

You can find the Parasail Batch Helper Library on Github. This library is 100% compatible with both Parasail and OpenAI openai-batch GitHub repository.

The first step is to create a Parasail API key: Create API Key. This key should be stored in your environment through something like a .bashrc file or a .env file, or passed through the command line invocation. Pasting directly in code isn't recommended as keys can get leaked.

Next, install openai-batch, the batch helper library that's compatible both with Parasail and OpenAI:

pip install openai-batch

Now you're ready to run a batch job in as little as five lines of code. The batch endpoint supports most transformers on Hugging Face—all you have to do is put the Hugging Face ID in the request. In this example, Parasail uses NousResearch/DeepHermes-3-Mistral-24 B-Preview (DeepHermes-3-Mistral-24B-Preview).

#test_batch.py
import random
from openai_batch import Batch

# Create a batch with random prompts
with Batch() as batch:
    objects = ["cat", "robot", "coffee mug", "spaceship", "banana"]
    for i in range(100):
        batch.add_to_batch(
            model="NousResearch/DeepHermes-3-Mistral-24B-Preview",
            messages=[{"role": "user", "content": f"Tell me a joke about a {random.choice(objects)}"}]
        )
    # Submit, wait for completion, and download results
    result, output_path, error_path = batch.submit_wait_download()
    print(f"Batch completed with status {result.status} and stored in {output_path}")

This code looks for PARASAIL_API_KEY in the environment, and passing it through the command line is straightforward. Running this code produces the following output:

PARASAIL_API_KEY=<INSERT API KEY> python3 test_batch.py
validating
in_progress
...
in_progress
in_progress
completed
Batch completed with status completed and stored in batch-itvt3wmjs7-output.jsonl

The first two lines of batch-itvt3wmjs7-output.jsonl are the prompt responses:

{"id":"vllm-51653b28a97e4e67a0d3587f959ffe3a","custom_id":"line-1","response":{"status_code":200,"request_id":"vllm-batch-1c7186c472cd49b1aa12a81760094540","body":{"id":"chatcmpl-01be171caf3b4dc69cfa9ef360d26a4e","object":"chat.completion","created":1743050291,"model":"NousResearch/DeepHermes-3-Mistral-24B-Preview","choices":[{"index":0,"message":{"role":"assistant","reasoning_content":null,"content":"Why did the coffee mug get arrested? It had too much to behave!","tool_calls":[]},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":41,"total_tokens":60,"completion_tokens":19,"prompt_tokens_details":null},"prompt_logprobs":null}},"error":null}
{"id":"vllm-58a8ac3f589d4380ad94e00b191da24e","custom_id":"line-3","response":{"status_code":200,"request_id":"vllm-batch-2dd59bd942fa4a25a8792f9b8ee28da1","body":{"id":"chatcmpl-a59bfccd7d134981bf5e1004e77c6854","object":"chat.completion","created":1743050291,"model":"NousResearch/DeepHermes-3-Mistral-24B-Preview","choices":[{"index":0,"message":{"role":"assistant","reasoning_content":null,"content":"Why can't you trust an astronaut? Because they're always out of this world!","tool_calls":[]},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":41,"total_tokens":59,"completion_tokens":18,"prompt_tokens_details":null},"prompt_logprobs":null}},"error":null}

Batch Submission Limitations

Both Parasail and OpenAI limit the maximum size of the batch input files:

Up to 50,000 requests (lines)
Up to 1000 MB total input file size for Parasail
Up to 250 MB total input file size for OpenAI
Max completion tokens for Parasail defaults to 8,192, but can be overridden to 16,384 through the max_completion_tokens parameter.

Workloads that exceed these limits must be split into multiple batches. The add_to_batch function in the Parasail Batch Helper Library will raise a ValueError exception when the file size or request count is exceeded for the provider.

Resuming Batch Jobs

A major convenience of batch processing is the ability to submit a job and resume the monitoring in a different process or flow. A developer can upload hundreds of batch jobs and millions of prompts without worrying about program crashes, errors, or resets—those prompts are processed on Parasail's servers until successful completion.

Changing the last two lines of the previous example submits the job and prints out the batch ID, then exits.

# Submit, wait for completion, and download results
batch_id = batch.submit()
print(f"Batch ID: {batch_id}")

With a batch ID of batch-tclfzwczcd, you can now wait for the batch to finish and download it in a separate script:

from openai_batch import Batch
import time

with Batch(batch_id="batch-tclfzwczcd",
           output_file="mybatch.jsonl") as batch:
    # Check status periodically
    while True:
        status = batch.status()
        print(f"Batch status: {status.status}")

if status.status in ["completed", "failed", "expired", "cancelled"]:
            break

time.sleep(60)  # Check every minute

# Download results once completed
    output_path, error_path = batch.download()
    print(f"Output saved to: {output_path}")

Which outputs:

Batch status: in_progress
...
Batch status: in_progress
Output saved to: mybatch.jsonl

Broad Model and Parameter Support

Chat completions, embeddings, multimodal inputs, the full range of prompt parameters, and even OpenAI models are supported.

OpenAI Models

with Batch() as batch:
    for i in range(100):
        batch.add_to_batch(
            model="gpt-4o",
            messages=[{"role": "user", "content": f"Give me 10 dad jokes"}]
        )

Embedding Models

GritLM—developed by Contextual and hosted on Hugging Face by Parasail—and GTE-Qwen2-7 B-Instruct from Alibaba are two excellent open source embedding models that rival proprietary models. Embeddings like these can be easily run by changing messages to input.

parasail-ai/GritLM-7 B-vllm

Alibaba-NLP/gte-Qwen2-7 B-instruct

As seen below, Parasail strongly recommends using base64 encoding encoding_format="base64" to reduce the size of the output files for both Parasail and OpenAI.

with Batch() as batch:
    for i in range(100):
        batch.add_to_batch(
            model="parasail-ai/GritLM-7B-vllm",
            encoding_format="base64",
            input=f"This is input #{i}",
        )

Parameters

add_to_batch supports all of the parameters that client.chat.completions.create or client.embedding.create supports, though note that open source models on Parasail may not always support every parameter.

with Batch() as batch:
    for i in range(100):
        batch.add_to_batch(
            model="NousResearch/DeepHermes-3-Mistral-24B-Preview",
            max_completion_tokens=1000,
            temperature=0.7,
            top_p=0.1,
            messages=[{"role": "user", "content": f"Give me 10 dad jokes"}]
        )

Metadata

You can add metadata to the batch. This is useful for passing information between separate submit and download processes, as well as tracking the results on the status UI page. Any metadata you add to the submission is visible in the Batch UI progress section. For detailed information about the metadata field, see the OpenAI Batch API Submit Specification.

with Batch() as batch:
    for i in range(100):
        batch.add_to_batch(
            model="NousResearch/DeepHermes-3-Mistral-24B-Preview",
            messages=[{"role": "user", "content": f"Give me 10 dad jokes"}]
        )
    batch.submit(metadata={"Job Name": "Dad jokes"})

Private Models

Batch can process private Hugging Face models by using a Dedicated deployment as the model source.

Create a Dedicated deployment with the private Hugging Face model. See Private Hugging Face Models.
Copy the Dedicated endpoint name from the deployment page.
Use that endpoint name as the model value in the batch request.
Pause the Dedicated deployment if you don't need it for online traffic; Batch uses the deployment metadata to locate the model and Hugging Face token.

Everything else in the Batch workflow stays the same.

Batch Image Understanding

The openai-batch helper can submit image understanding jobs. It reads local image files, converts them to Base64, inserts them into the batch request, and stores model outputs in the output directory.

pip install openai-batch

See the image understanding example in the openai-batch repository. For multimodal request shapes, see Multi-Modal.

Parasail Batch UI

The Parasail Batch UI can be used to upload new batches, track the status of batches, and download results when finished.

While a batch is queued or running, you can view its status, download the input, or cancel it:

When a batch job is finished, you can download the input and the output file as well as view the total token usage.