Skip to main content

LoRAX Python Client

Project description

LoRAX Python Client

LoRAX Python client provides a convenient way of interfacing with a lorax instance running in your environment.

Getting Started

Install

pip install lorax-client

Run

from lorax import Client

endpoint_url = "http://127.0.0.1:8080"

client = Client(endpoint_url)
text = client.generate("Why is the sky blue?", adapter_id="some/adapter").generated_text
print(text)
# ' Rayleigh scattering'

# Token Streaming
text = ""
for response in client.generate_stream("Why is the sky blue?", adapter_id="some/adapter"):
    if not response.token.special:
        text += response.token.text

print(text)
# ' Rayleigh scattering'

or with the asynchronous client:

from lorax import AsyncClient

endpoint_url = "http://127.0.0.1:8080"

client = AsyncClient(endpoint_url)
response = await client.generate("Why is the sky blue?", adapter_id="some/adapter")
print(response.generated_text)
# ' Rayleigh scattering'

# Token Streaming
text = ""
async for response in client.generate_stream("Why is the sky blue?", adapter_id="some/adapter"):
    if not response.token.special:
        text += response.token.text

print(text)
# ' Rayleigh scattering'

Predibase Inference Endpoints

The LoRAX client can also be used to connect to Predibase managed LoRAX endpoints (including Predibase's serverless endpoints).

You need only make the following changes to the above examples:

  1. Change the endpoint_url to match the endpoint of your Predibase LLM of choice.
  2. Provide your Predibase API token in the headers provided to the client.

Example:

from lorax import Client

endpoint_url = f"https://api.app.predibase.com/v1/llms/{llm_deployment_name}"
headers = {
    "Authorization": f"Bearer {api_token}"
}

client = Client(endpoint_url, headers=headers)

# same as above from here ...
response = client.generate("Why is the sky blue?", adapter_id=f"{model_repo}/{model_version}")

Note that by default Predibase will use its internal model repos as the default adapter_source. To use an adapter from Huggingface:

response = client.generate("Why is the sky blue?", adapter_id="some/adapter", adapter_source="hub")

Types

# Request Parameters
class Parameters:
    # The ID of the adapter to use
    adapter_id: Optional[str]
    # The source of the adapter to use
    adapter_source: Optional[str]
    # Activate logits sampling
    do_sample: bool
    # Maximum number of generated tokens
    max_new_tokens: int
    # The parameter for repetition penalty. 1.0 means no penalty.
    # See [this paper](https://arxiv.org/pdf/1909.05858.pdf) for more details.
    repetition_penalty: Optional[float]
    # Whether to prepend the prompt to the generated text
    return_full_text: bool
    # Stop generating tokens if a member of `stop_sequences` is generated
    stop: List[str]
    # Random sampling seed
    seed: Optional[int]
    # The value used to module the logits distribution.
    temperature: Optional[float]
    # The number of highest probability vocabulary tokens to keep for top-k-filtering.
    top_k: Optional[int]
    # If set to < 1, only the smallest set of most probable tokens with probabilities that add up to `top_p` or
    # higher are kept for generation.
    top_p: Optional[float]
    # truncate inputs tokens to the given size
    truncate: Optional[int]
    # Typical Decoding mass
    # See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information
    typical_p: Optional[float]
    # Generate best_of sequences and return the one if the highest token logprobs
    best_of: Optional[int]
    # Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
    watermark: bool
    # Get decoder input token logprobs and ids
    decoder_input_details: bool
    # The number of highest probability vocabulary tokens to return as alternative tokens in the generation result
    return_k_alternatives: Optional[int]

# Decoder input tokens
class InputToken:
    # Token ID from the model tokenizer
    id: int
    # Token text
    text: str
    # Logprob
    # Optional since the logprob of the first token cannot be computed
    logprob: Optional[float]


# Generated tokens
class Token:
    # Token ID from the model tokenizer
    id: int
    # Token text
    text: str
    # Logprob
    logprob: float
    # Is the token a special token
    # Can be used to ignore tokens when concatenating
    special: bool


# Generation finish reason
class FinishReason(Enum):
    # number of generated tokens == `max_new_tokens`
    Length = "length"
    # the model generated its end of sequence token
    EndOfSequenceToken = "eos_token"
    # the model generated a text included in `stop_sequences`
    StopSequence = "stop_sequence"


# Additional sequences when using the `best_of` parameter
class BestOfSequence:
    # Generated text
    generated_text: str
    # Generation finish reason
    finish_reason: FinishReason
    # Number of generated tokens
    generated_tokens: int
    # Sampling seed if sampling was activated
    seed: Optional[int]
    # Decoder input tokens, empty if decoder_input_details is False
    prefill: List[InputToken]
    # Generated tokens
    tokens: List[Token]


# `generate` details
class Details:
    # Generation finish reason
    finish_reason: FinishReason
    # Number of prompt tokens
    prompt_tokens: int
    # Number of generated tokens
    generated_tokens: int
    # Sampling seed if sampling was activated
    seed: Optional[int]
    # Decoder input tokens, empty if decoder_input_details is False
    prefill: List[InputToken]
    # Generated tokens
    tokens: List[Token]
    # Additional sequences when using the `best_of` parameter
    best_of_sequences: Optional[List[BestOfSequence]]


# `generate` return value
class Response:
    # Generated text
    generated_text: str
    # Generation details
    details: Details


# `generate_stream` details
class StreamDetails:
    # Generation finish reason
    finish_reason: FinishReason
    # Number of prompt tokens
    prompt_tokens: int
    # Number of generated tokens
    generated_tokens: int
    # Sampling seed if sampling was activated
    seed: Optional[int]


# `generate_stream` return value
class StreamResponse:
    # Generated token
    token: Token
    # Complete generated text
    # Only available when the generation is finished
    generated_text: Optional[str]
    # Generation details
    # Only available when the generation is finished
    details: Optional[StreamDetails]

# Inference API currently deployed model
class DeployedModel:
    model_id: str
    sha: str

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lorax_client-0.6.3.tar.gz (10.8 kB view details)

Uploaded Source

Built Distribution

lorax_client-0.6.3-py3-none-any.whl (12.0 kB view details)

Uploaded Python 3

File details

Details for the file lorax_client-0.6.3.tar.gz.

File metadata

  • Download URL: lorax_client-0.6.3.tar.gz
  • Upload date:
  • Size: 10.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.1 CPython/3.8.16 Darwin/24.0.0

File hashes

Hashes for lorax_client-0.6.3.tar.gz
Algorithm Hash digest
SHA256 37216d9debd3483e81361ca6686964a8d767bf3e4d65866e42132adacd084d33
MD5 706304eefccf6b8b9180f4ad22a0beed
BLAKE2b-256 61a9fe174a6b64996120c23236c103f536412c6bf2c40624eb9bfb42c28ef050

See more details on using hashes here.

File details

Details for the file lorax_client-0.6.3-py3-none-any.whl.

File metadata

  • Download URL: lorax_client-0.6.3-py3-none-any.whl
  • Upload date:
  • Size: 12.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.1 CPython/3.8.16 Darwin/24.0.0

File hashes

Hashes for lorax_client-0.6.3-py3-none-any.whl
Algorithm Hash digest
SHA256 097db7f262e592dfc1fd5858329e8207bf67e9aeb5671f257330a0f300abcb88
MD5 c52c690ae14366c7c49ad05b6b380be9
BLAKE2b-256 77fd29f348a0c264f63171ee4c4969a646cd84a740e424b8d438a9333e2fe6cf

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page