AI21Labs · Josephasafg · Mar 13, 2025 · Mar 13, 2025 · Mar 13, 2025 · Mar 13, 2025
diff --git a/README.md b/README.md
@@ -21,15 +21,13 @@
 ## Table of Contents
 
 - [Examples](#examples-tldr) 🗂️
-- [Migration from v1.3.4 and below](#migration-from-v134-and-below)
 - [AI21 Official Documentation](#Documentation)
 - [Installation](#Installation) 💿
 - [Usage - Chat Completions](#Usage)
 - [Conversational RAG (Beta)](#Conversational-RAG-Beta)
 - [Older Models Support Usage](#Older-Models-Support-Usage)
 - [More Models](#More-Models)
   - [Streaming](#Streaming)
-  - [TSMs](#TSMs)
 - [Token Counting](#Token-Counting)
 - [Environment Variables](#Environment-Variables)
 - [Error Handling](#Error-Handling)
@@ -48,101 +46,6 @@ If you want to quickly get a glance how to use the AI21 Python SDK and jump stra
 
 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.
-
-<details>
-<summary>Migration Examples</summary>
-
-### Instance creation (not available in v1.3.4 and below)
-
-```python
-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
-
-```diff
-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
-
-```diff
-- 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.
-
-```diff
-- 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
-
-```diff
-- 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
-
-```diff
-- 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)
-```
-
-</details>
-
 ## Documentation
 
 ---
@@ -220,20 +123,6 @@ asyncio.run(main())
 
 A more detailed example can be found [here](examples/studio/chat/chat_completions.py).
 
-## Older Models Support Usage
-
-<details>
-<summary>Examples</summary>
-
-### Supported Models:
-
-- j2-light
-- [j2-ultra](#Chat)
-- [j2-mid](#Completion)
-- [jamba-instruct](#Chat-Completion)
-
-you can read more about the models [here](https://docs.ai21.com/reference/j2-complete-api-ref#jurassic-2-models).
-
 ### Chat
 
 ```python

diff --git a/ai21/clients/bedrock/ai21_bedrock_client.py b/ai21/clients/bedrock/ai21_bedrock_client.py
@@ -10,10 +10,6 @@
 from ai21.clients.aws.aws_authorization import AWSAuthorization
 from ai21.clients.bedrock._stream_decoder import _AWSEventStreamDecoder
 from ai21.clients.studio.resources.studio_chat import AsyncStudioChat, StudioChat
-from ai21.clients.studio.resources.studio_completion import (
-    AsyncStudioCompletion,
-    StudioCompletion,
-)
 from ai21.errors import AccessDenied, APITimeoutError, ModelErrorException, NotFound
 from ai21.http_client.async_http_client import AsyncAI21HTTPClient
 from ai21.http_client.http_client import AI21HTTPClient
@@ -101,10 +97,6 @@ def __init__(
         BaseBedrockClient.__init__(self, session=session, region=self._region)
 
         self.chat = StudioChat(self)
-        # Override the chat.create method to match the completions endpoint,
-        # so it wouldn't get to the old J2 completion endpoint
-        self.chat.create = self.chat.completions.create
-        self.completion = StudioCompletion(self)
 
     def _build_request(self, options: RequestOptions) -> httpx.Request:
         options = self._prepare_options(options)
@@ -146,10 +138,7 @@ def __init__(
         BaseBedrockClient.__init__(self, session=session, region=self._region)
 
         self.chat = AsyncStudioChat(self)
-        # Override the chat.create method to match the completions endpoint,
-        # so it wouldn't get to the old J2 completion endpoint
         self.chat.create = self.chat.completions.create
-        self.completion = AsyncStudioCompletion(self)
 
     def _build_request(self, options: RequestOptions) -> httpx.Request:
         options = self._prepare_options(options)

diff --git a/ai21/clients/common/completion_base.py b/ai21/clients/common/completion_base.py
diff --git a/ai21/clients/studio/resources/studio_completion.py b/ai21/clients/studio/resources/studio_completion.py
diff --git a/ai21/models/__init__.py b/ai21/models/__init__.py
@@ -2,17 +2,14 @@
 from ai21.models.chat_message import ChatMessage
 from ai21.models.document_type import DocumentType
 from ai21.models.penalty import Penalty
-from ai21.models.responses.chat_response import ChatResponse, ChatOutput, FinishReason
-from ai21.models.responses.completion_response import (
-    CompletionsResponse,
-    Completion,
-    CompletionFinishReason,
-    CompletionData,
-    Prompt,
+from ai21.models.responses.chat_response import ChatOutput, ChatResponse, FinishReason
+from ai21.models.responses.conversational_rag_response import (
+    ConversationalRagResponse,
+    ConversationalRagSource,
 )
-from ai21.models.responses.conversational_rag_response import ConversationalRagResponse, ConversationalRagSource
 from ai21.models.responses.file_response import FileResponse
 
+
 __all__ = [
     "ChatMessage",
     "RoleType",
@@ -21,11 +18,6 @@
     "ChatResponse",
     "ChatOutput",
     "FinishReason",
-    "CompletionsResponse",
-    "Completion",
-    "CompletionFinishReason",
-    "CompletionData",
-    "Prompt",
     "FileResponse",
     "ConversationalRagResponse",
     "ConversationalRagSource",