No project description provided

These details have been verified by PyPI

Maintainers

ai21 amirkai21 antonn.ai21.com asaf_gardin ellanAI21 Haimon

These details have not been verified by PyPI

Project description

AI21 Labs Python SDK

Examples 🗂️
Migration from v1.3.4 and below
AI21 Official Documentation
Installation 💿
Usage - Chat Completions
Conversational RAG (Beta)
Older Models Support Usage
More Models
- Streaming
- TSMs
Token Counting
Environment Variables
Error Handling
Cloud Providers ☁️
- AWS
  - Bedrock
  - SageMaker
- Azure
- Vertex

Examples (tl;dr)

If you want to quickly get a glance how to use the AI21 Python SDK and jump straight to business, you can check out the examples. Take a look at our models and see them in action! Several examples and demonstrations have been put together to show our models' functionality and capabilities.

Check out the Examples

Feel free to dive in, experiment, and adapt these examples to suit your needs. We believe they'll help you get up and running quickly.

Migration from v1.3.4 and below

In v2.0.0 we introduced a new SDK that is not backwards compatible with the previous version. This version allows for non-static instances of the client, defined parameters to each resource, modelized responses and more.

Migration Examples

Instance creation (not available in v1.3.4 and below)

from ai21 import AI21Client

client = AI21Client(api_key='my_api_key')

# or set api_key in environment variable - AI21_API_KEY and then
client = AI21Client()

We No longer support static methods for each resource, instead we have a client instance that has a method for each allowing for more flexibility and better control.

Completion before/after

prompt = "some prompt"

- import ai21
- response = ai21.Completion.execute(model="j2-light", prompt=prompt, maxTokens=2)

+ from ai21 import AI21Client
+ client = ai21.AI21Client()
+ response = client.completion.create(model="j2-light", prompt=prompt, max_tokens=2)

This applies to all resources. You would now need to create a client instance and use it to call the resource method.

Tokenization and Token counting before/after

- response = ai21.Tokenization.execute(text=prompt)
- print(len(response)) # number of tokens

+ from ai21 import AI21Client
+ client = AI21Client()
+ token_count = client.count_tokens(text=prompt)

Key Access in Response Objects before/after

It is no longer possible to access the response object as a dictionary. Instead, you can access the response object as an object with attributes.

- import ai21
- response = ai21.Summarize.execute(source="some text", sourceType="TEXT")
- response["summary"]

+ from ai21 import AI21Client
+ from ai21.models import DocumentType
+ client = AI21Client()
+ response = client.summarize.create(source="some text", source_type=DocumentType.TEXT)
+ response.summary

AWS Client Creations

Bedrock Client creation before/after

- import ai21
- destination = ai21.BedrockDestination(model_id=ai21.BedrockModelID.J2_MID_V1)
- response = ai21.Completion.execute(prompt=prompt, maxTokens=1000, destination=destination)

+ from ai21 import AI21BedrockClient, BedrockModelID
+ client = AI21BedrockClient()
+ response = client.completion.create(prompt=prompt, max_tokens=1000, model_id=BedrockModelID.J2_MID_V1)

SageMaker Client creation before/after

- import ai21
- destination = ai21.SageMakerDestination("j2-mid-test-endpoint")
- response = ai21.Completion.execute(prompt=prompt, maxTokens=1000, destination=destination)

+ from ai21 import AI21SageMakerClient
+ client = AI21SageMakerClient(endpoint_name="j2-mid-test-endpoint")
+ response = client.completion.create(prompt=prompt, max_tokens=1000)

Documentation

The full documentation for the REST API can be found on docs.ai21.com.

Installation

pip install ai21

Usage

from ai21 import AI21Client
from ai21.models.chat import ChatMessage

client = AI21Client(
    # defaults to os.enviorn.get('AI21_API_KEY')
    api_key='my_api_key',
)

system = "You're a support engineer in a SaaS company"
messages = [
    ChatMessage(content=system, role="system"),
    ChatMessage(content="Hello, I need help with a signup process.", role="user"),
]

chat_completions = client.chat.completions.create(
    messages=messages,
    model="jamba-1.5-mini",
)

Async Usage

You can use the AsyncAI21Client to make asynchronous requests. There is no difference between the sync and the async client in terms of usage.

import asyncio

from ai21 import AsyncAI21Client
from ai21.models.chat import ChatMessage

system = "You're a support engineer in a SaaS company"
messages = [
    ChatMessage(content=system, role="system"),
    ChatMessage(content="Hello, I need help with a signup process.", role="user"),
]

client = AsyncAI21Client(
   # defaults to os.enviorn.get('AI21_API_KEY')
    api_key='my_api_key',
)


async def main():
    response = await client.chat.completions.create(
        messages=messages,
        model="jamba-1.5-mini",
    )

    print(response)


asyncio.run(main())

A more detailed example can be found here.

Older Models Support Usage

Examples

Supported Models:

j2-light
j2-ultra
j2-mid
jamba-instruct

you can read more about the models here.

Chat

from ai21 import AI21Client
from ai21.models import RoleType
from ai21.models import ChatMessage

system = "You're a support engineer in a SaaS company"
messages = [
    ChatMessage(text="Hello, I need help with a signup process.", role=RoleType.USER),
    ChatMessage(text="Hi Alice, I can help you with that. What seems to be the problem?", role=RoleType.ASSISTANT),
    ChatMessage(text="I am having trouble signing up for your product with my Google account.", role=RoleType.USER),
]


client = AI21Client()
chat_response = client.chat.create(
    system=system,
    messages=messages,
    model="j2-ultra",
)

For a more detailed example, see the chat examples.

Completion

from ai21 import AI21Client


client = AI21Client()
completion_response = client.completion.create(
    prompt="This is a test prompt",
    model="j2-mid",
)

Chat Completion

from ai21 import AI21Client
from ai21.models.chat import ChatMessage

system = "You're a support engineer in a SaaS company"
messages = [
    ChatMessage(content=system, role="system"),
    ChatMessage(content="Hello, I need help with a signup process.", role="user"),
    ChatMessage(content="Hi Alice, I can help you with that. What seems to be the problem?", role="assistant"),
    ChatMessage(content="I am having trouble signing up for your product with my Google account.", role="user"),
]

client = AI21Client()

response = client.chat.completions.create(
    messages=messages,
    model="jamba-instruct",
    max_tokens=100,
    temperature=0.7,
    top_p=1.0,
    stop=["\n"],
)

print(response)

Note that jamba-instruct supports async and streaming as well.

For a more detailed example, see the completion examples.

Streaming

We currently support streaming for the Chat Completions API in Jamba.

from ai21 import AI21Client
from ai21.models.chat import ChatMessage

messages = [ChatMessage(content="What is the meaning of life?", role="user")]

client = AI21Client()

response = client.chat.completions.create(
    messages=messages,
    model="jamba-instruct",
    stream=True,
)
for chunk in response:
    print(chunk.choices[0].delta.content, end="")

Async Streaming

import asyncio

from ai21 import AsyncAI21Client
from ai21.models.chat import ChatMessage

messages = [ChatMessage(content="What is the meaning of life?", role="user")]

client = AsyncAI21Client()


async def main():
    response = await client.chat.completions.create(
        messages=messages,
        model="jamba-1.5-mini",
        stream=True,
    )
    async for chunk in response:
        print(chunk.choices[0].delta.content, end="")


asyncio.run(main())

Conversational RAG (Beta)

Like chat, but with the ability to retrieve information from your Studio library.

from ai21 import AI21Client
from ai21.models.chat import ChatMessage

messages = [
    ChatMessage(content="Ask a question about your files", role="user"),
]

client = AI21Client()

client.library.files.create(
  file_path="path/to/file",
  path="path/to/file/in/library",
  labels=["my_file_label"],
)
chat_response = client.beta.conversational_rag.create(
    messages=messages,
    labels=["my_file_label"],
)

For a more detailed example, see the chat sync and async examples.

More Models

TSMs

AI21 Studio's Task-Specific Models offer a range of powerful tools. These models have been specifically designed for their respective tasks and provide high-quality results while optimizing efficiency. The full documentation and guides can be found here.

Contextual Answers

The answer API allows you to access our high-quality question answering model.

from ai21 import AI21Client

client = AI21Client()
response = client.answer.create(
    context="This is a text is for testing purposes",
    question="Question about context",
)

A detailed explanation on Contextual Answers, can be found here

File Upload

from ai21 import AI21Client

client = AI21Client()

file_id = client.library.files.create(
    file_path="path/to/file",
    path="path/to/file/in/library",
    labels=["label1", "label2"],
    public_url="www.example.com",
)

uploaded_file = client.library.files.get(file_id)

For more information on more Task Specific Models, see the documentation.

Token Counting

By using the count_tokens method, you can estimate the billing for a given request.

from ai21.tokenizers import get_tokenizer

tokenizer = get_tokenizer(name="jamba-tokenizer")
total_tokens = tokenizer.count_tokens(text="some text")  # returns int
print(total_tokens)

Async Usage

from ai21.tokenizers import get_async_tokenizer

## Your async function code
#...
tokenizer = await get_async_tokenizer(name="jamba-tokenizer")
total_tokens = await tokenizer.count_tokens(text="some text")  # returns int
print(total_tokens)

Available tokenizers are:

jamba-tokenizer
j2-tokenizer

For more information on AI21 Tokenizers, see the documentation.

Environment Variables

You can set several environment variables to configure the client.

Logging

We use the standard library logging module.

To enable logging, set the AI21_LOG_LEVEL environment variable.

$ export AI21_LOG_LEVEL=debug

Other Important Environment Variables

AI21_API_KEY - Your API key. If not set, you must pass it to the client constructor.
AI21_API_VERSION - The API version. Defaults to v1.
AI21_API_HOST - The API host. Defaults to https://api.ai21.com/v1/.
AI21_TIMEOUT_SEC - The timeout for API requests.
AI21_NUM_RETRIES - The maximum number of retries for API requests. Defaults to 3 retries.
AI21_AWS_REGION - The AWS region to use for AWS clients. Defaults to us-east-1.

Error Handling

from ai21 import errors as ai21_errors
from ai21 import AI21Client, AI21APIError
from ai21.models import ChatMessage

client = AI21Client()

system = "You're a support engineer in a SaaS company"
messages = [
        # Notice the given role does not exist and will be the reason for the raised error
        ChatMessage(text="Hello, I need help with a signup process.", role="Non-Existent-Role"),
    ]

try:
    chat_completion = client.chat.create(
        messages=messages,
        model="j2-ultra",
        system=system
    )
except ai21_errors.AI21ServerError as e:
    print("Server error and could not be reached")
    print(e.details)
except ai21_errors.TooManyRequestsError as e:
    print("A 429 status code was returned. Slow down on the requests")
except AI21APIError as e:
    print("A non 200 status code error. For more error types see ai21.errors")

Cloud Providers

AWS

AI21 Library provides convenient ways to interact with two AWS clients for use with AWS Bedrock and AWS SageMaker.

Installation

pip install -U "ai21[AWS]"

This will make sure you have the required dependencies installed, including boto3 >= 1.28.82.

Usage

Bedrock

from ai21 import AI21BedrockClient, BedrockModelID
from ai21.models.chat import ChatMessage

client = AI21BedrockClient(region='us-east-1') # region is optional, as you can use the env variable instead

messages = [
  ChatMessage(content="You are a helpful assistant", role="system"),
  ChatMessage(content="What is the meaning of life?", role="user")
]

response = client.chat.completions.create(
    messages=messages,
    model_id=BedrockModelID.JAMBA_1_5_LARGE,
)

Stream

from ai21 import AI21BedrockClient, BedrockModelID
from ai21.models.chat import ChatMessage

system = "You're a support engineer in a SaaS company"
messages = [
    ChatMessage(content=system, role="system"),
    ChatMessage(content="Hello, I need help with a signup process.", role="user"),
    ChatMessage(content="Hi Alice, I can help you with that. What seems to be the problem?", role="assistant"),
    ChatMessage(content="I am having trouble signing up for your product with my Google account.", role="user"),
]

client = AI21BedrockClient()

response = client.chat.completions.create(
    messages=messages,
    model=BedrockModelID.JAMBA_1_5_LARGE,
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].message.content, end="")

Async

import asyncio
from ai21 import AsyncAI21BedrockClient, BedrockModelID
from ai21.models.chat import ChatMessage

client = AsyncAI21BedrockClient(region='us-east-1') # region is optional, as you can use the env variable instead

messages = [
  ChatMessage(content="You are a helpful assistant", role="system"),
  ChatMessage(content="What is the meaning of life?", role="user")
]

async def main():
    response = await client.chat.completions.create(
        messages=messages,
        model_id=BedrockModelID.JAMBA_1_5_LARGE,
    )


asyncio.run(main())

With Boto3 Session

import boto3

from ai21 import AI21BedrockClient, BedrockModelID
from ai21.models.chat import ChatMessage

boto_session = boto3.Session(region_name="us-east-1")

client = AI21BedrockClient(session=boto_session)

messages = [
  ChatMessage(content="You are a helpful assistant", role="system"),
  ChatMessage(content="What is the meaning of life?", role="user")
]

response = client.chat.completions.create(
    messages=messages,
    model_id=BedrockModelID.JAMBA_1_5_LARGE,
)

Async

import boto3
import asyncio

from ai21 import AsyncAI21BedrockClient, BedrockModelID
from ai21.models.chat import ChatMessage

boto_session = boto3.Session(region_name="us-east-1")

client = AsyncAI21BedrockClient(session=boto_session)

messages = [
  ChatMessage(content="You are a helpful assistant", role="system"),
  ChatMessage(content="What is the meaning of life?", role="user")
]

async def main():
  response = await client.chat.completions.create(
      messages=messages,
      model_id=BedrockModelID.JAMBA_1_5_LARGE,
  )

asyncio.run(main())

SageMaker

from ai21 import AI21SageMakerClient

client = AI21SageMakerClient(endpoint_name="j2-endpoint-name")
response = client.summarize.create(
    source="Text to summarize",
    source_type="TEXT",
)
print(response.summary)

Async

import asyncio
from ai21 import AsyncAI21SageMakerClient

client = AsyncAI21SageMakerClient(endpoint_name="j2-endpoint-name")

async def main():
  response = await client.summarize.create(
      source="Text to summarize",
      source_type="TEXT",
  )
  print(response.summary)

asyncio.run(main())

With Boto3 Session

from ai21 import AI21SageMakerClient
import boto3
boto_session = boto3.Session(region_name="us-east-1")

client = AI21SageMakerClient(
    session=boto_session,
    endpoint_name="j2-endpoint-name",
)

Azure

If you wish to interact with your Azure endpoint on Azure AI Studio, use the AI21AzureClient and AsyncAI21AzureClient clients.

The following models are supported on Azure:

jamba-instruct

from ai21 import AI21AzureClient
from ai21.models.chat import ChatMessage

client = AI21AzureClient(
  base_url="https://<YOUR-ENDPOINT>.inference.ai.azure.com",
  api_key="<your Azure api key>",
)

messages = [
  ChatMessage(content="You are a helpful assistant", role="system"),
  ChatMessage(content="What is the meaning of life?", role="user")
]

response = client.chat.completions.create(
  model="jamba-1.5-mini",
  messages=messages,
)

Async

import asyncio
from ai21 import AsyncAI21AzureClient
from ai21.models.chat import ChatMessage

client = AsyncAI21AzureClient(
  base_url="https://<YOUR-ENDPOINT>.inference.ai.azure.com/v1/chat/completions",
  api_key="<your Azure api key>",
)

messages = [
  ChatMessage(content="You are a helpful assistant", role="system"),
  ChatMessage(content="What is the meaning of life?", role="user")
]

async def main():
  response = await client.chat.completions.create(
    model="jamba-instruct",
    messages=messages,
  )

asyncio.run(main())

Vertex

If you wish to interact with your Vertex AI endpoint on GCP, use the AI21VertexClient and AsyncAI21VertexClient clients.

The following models are supported on Vertex:

jamba-1.5-mini
jamba-1.5-large

from ai21 import AI21VertexClient

from ai21.models.chat import ChatMessage

# You can also set the project_id, region, access_token and Google credentials in the constructor
client = AI21VertexClient()

messages = ChatMessage(content="What is the meaning of life?", role="user")

response = client.chat.completions.create(
    model="jamba-1.5-mini",
    messages=[messages],
)

Async

import asyncio

from ai21 import AsyncAI21VertexClient
from ai21.models.chat import ChatMessage

# You can also set the project_id, region, access_token and Google credentials in the constructor
client = AsyncAI21VertexClient()


async def main():
    messages = ChatMessage(content="What is the meaning of life?", role="user")

    response = await client.chat.completions.create(
        model="jamba-1.5-mini",
        messages=[messages],
    )

asyncio.run(main())

Happy prompting! 🚀

Project details

These details have been verified by PyPI

Maintainers

ai21 amirkai21 antonn.ai21.com asaf_gardin ellanAI21 Haimon

These details have not been verified by PyPI

Release history Release notifications | RSS feed

3.0.0

Nov 11, 2024

2.16.0 yanked

Nov 11, 2024

This version

2.15.2

Nov 5, 2024

2.15.1

Sep 30, 2024

2.15.0

Sep 24, 2024

2.14.1

Aug 26, 2024

2.14.0

Aug 22, 2024

2.13.0

Aug 21, 2024

2.13.0rc2 pre-release

Aug 21, 2024

2.13.0rc1 pre-release

Aug 20, 2024

2.12.0

Aug 7, 2024

2.11.0

Aug 6, 2024

2.10.1

Jul 31, 2024

2.10.0

Jul 29, 2024

2.10.0rc1 pre-release

Jul 28, 2024

2.9.2

Jul 15, 2024

2.9.1

Jul 10, 2024

2.9.0

Jul 7, 2024

2.8.0

Jun 26, 2024

2.7.0

Jun 21, 2024

2.6.0

Jun 13, 2024

2.5.2

Jun 13, 2024

2.5.1

Jun 13, 2024

2.5.0

Jun 10, 2024

2.4.2

Jun 6, 2024

2.4.1

Jun 3, 2024

2.4.0

May 28, 2024

2.3.1

May 22, 2024

2.3.0

May 20, 2024

2.2.5

May 14, 2024

2.2.4

May 9, 2024

2.2.3

Apr 25, 2024

2.2.2

Apr 24, 2024

2.2.1

Apr 22, 2024

2.2.0

Apr 10, 2024

2.2.0rc2 pre-release

Apr 10, 2024

2.2.0rc1 pre-release

Mar 27, 2024

2.1.3

Mar 27, 2024

2.1.2

Feb 27, 2024

2.1.1

Feb 25, 2024

2.1.0

Feb 25, 2024

2.0.5

Feb 21, 2024

2.0.4

Feb 18, 2024

2.0.3

Feb 7, 2024

2.0.2

Feb 4, 2024

2.0.1

Feb 1, 2024

2.0.0

Jan 31, 2024

2.0.0rc12 pre-release

Jan 30, 2024

2.0.0rc11 pre-release

Jan 22, 2024

2.0.0rc10 pre-release

Jan 18, 2024

2.0.0rc9 pre-release

Jan 7, 2024

2.0.0rc8 pre-release

Jan 3, 2024

2.0.0rc7 pre-release

Jan 2, 2024

2.0.0rc6 pre-release

Jan 2, 2024

2.0.0rc5 pre-release

Dec 27, 2023

2.0.0rc4 pre-release

Dec 19, 2023

1.3.4

Jan 31, 2024

1.3.3

Dec 5, 2023

1.3.2

Nov 14, 2023

1.3.1

Nov 12, 2023

1.3.0

Nov 5, 2023

1.2.8

Sep 18, 2023

1.2.7

Sep 7, 2023

1.2.6

Aug 30, 2023

1.2.5

Aug 16, 2023

1.2.4

Aug 1, 2023

1.2.3

Aug 1, 2023

1.2.2

Jul 24, 2023

1.2.1

Jul 17, 2023

1.1.4

Jun 11, 2023

1.1.3

Jun 8, 2023

1.1.2

Jun 8, 2023

1.1.1

Jun 7, 2023

1.1.0 yanked

Jun 7, 2023

1.0.7

May 17, 2023

1.0.5

Apr 19, 2023

1.0.4

Apr 10, 2023

1.0.3

Mar 27, 2023

1.0.2

Mar 9, 2023

1.0.1

Mar 8, 2023

1.0.0

Mar 8, 2023

0.0.3

Dec 15, 2022

0.0.1

Nov 22, 2022

Download files

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

Source Distribution

ai21-2.15.2.tar.gz (51.7 kB view hashes)

Uploaded Nov 5, 2024 Source

Built Distribution

ai21-2.15.2-py3-none-any.whl (88.8 kB view hashes)

Uploaded Nov 5, 2024 Python 3

Hashes for ai21-2.15.2.tar.gz

Hashes for ai21-2.15.2.tar.gz
Algorithm	Hash digest
SHA256	`e43059fac8cd7ceb924962f4ead4a8ba9a397709577d6993c4304a92000e2036`
MD5	`2d7c1ed196f0b8c62ffe8e688eb0d38e`
BLAKE2b-256	`e4ad2a8dca64821b48d9b4b107c8859173f3639f7c01353370d30faa3b25bfc4`

Hashes for ai21-2.15.2-py3-none-any.whl

Hashes for ai21-2.15.2-py3-none-any.whl
Algorithm	Hash digest
SHA256	`7b42e5b0253192d487c724dc7b89b0693c104b0555c1ccc505bf53d135d98283`
MD5	`82da4733f288c305a28fb941e5d040e8`
BLAKE2b-256	`95547e8f8129236b91aabf8eaa3297194d863e5098dff1b7742d20962e2e1fc5`

ai21 2.15.2

Navigation

Verified details

Maintainers

Unverified details

Meta

Classifiers

Project description

AI21 Labs Python SDK

Table of Contents

Examples (tl;dr)

Check out the Examples

Migration from v1.3.4 and below

Instance creation (not available in v1.3.4 and below)

Completion before/after

Tokenization and Token counting before/after

Key Access in Response Objects before/after

AWS Client Creations

Bedrock Client creation before/after

SageMaker Client creation before/after

Documentation

Installation

Usage

Async Usage

Older Models Support Usage

Supported Models:

Chat

Completion

Chat Completion

Streaming

Async Streaming

Conversational RAG (Beta)

More Models

TSMs

Contextual Answers

File Upload

Token Counting

Async Usage

Environment Variables

Logging

Other Important Environment Variables

Error Handling

Cloud Providers

AWS

Installation

Usage

Bedrock

Stream

Async

With Boto3 Session

Async

SageMaker

Async

With Boto3 Session

Azure

Async

Vertex

Async

Project details

Verified details

Maintainers

Unverified details

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distribution