diff --git a/README.md b/README.md
index b6ab33b..2eaed3e 100644
--- a/README.md
+++ b/README.md
@@ -17,10 +17,9 @@ pip install ollama
 ## Usage
 
 ```python
-from ollama import chat
-from ollama import ChatResponse
+import ollama
 
-response: ChatResponse = chat(model='llama3.2', messages=[
+response: ollama.ChatResponse = ollama.chat(model='llama3.2', messages=[
   {
     'role': 'user',
     'content': 'Why is the sky blue?',
@@ -38,12 +37,12 @@ See [_types.py](ollama/_types.py) for more information on the response types.
 Response streaming can be enabled by setting `stream=True`.
 
 ```python
-from ollama import chat
+import ollama
 
-stream = chat(
-    model='llama3.2',
-    messages=[{'role': 'user', 'content': 'Why is the sky blue?'}],
-    stream=True,
+stream = ollama.chat(
+  model='llama3.2',
+  messages=[{'role': 'user', 'content': 'Why is the sky blue?'}],
+  stream=True,
 )
 
 for chunk in stream:
@@ -56,8 +55,9 @@ A custom client can be created by instantiating `Client` or `AsyncClient` from `
 All extra keyword arguments are passed into the [`httpx.Client`](https://www.python-httpx.org/api/#client).
 
 ```python
-from ollama import Client
-client = Client(
+import ollama
+
+client = ollama.Client(
   host='http://localhost:11434',
   headers={'x-some-header': 'some-value'}
 )
@@ -75,11 +75,12 @@ The `AsyncClient` class is used to make asynchronous requests. It can be configu
 
 ```python
 import asyncio
-from ollama import AsyncClient
+import ollama
+
 
 async def chat():
   message = {'role': 'user', 'content': 'Why is the sky blue?'}
-  response = await AsyncClient().chat(model='llama3.2', messages=[message])
+  response = await ollama.AsyncClient().chat(model='llama3.2', messages=[message])
 
 asyncio.run(chat())
 ```
@@ -88,11 +89,11 @@ Setting `stream=True` modifies functions to return a Python asynchronous generat
 
 ```python
 import asyncio
-from ollama import AsyncClient
+import ollama
 
 async def chat():
   message = {'role': 'user', 'content': 'Why is the sky blue?'}
-  async for part in await AsyncClient().chat(model='llama3.2', messages=[message], stream=True):
+  async for part in await ollama.AsyncClient().chat(model='llama3.2', messages=[message], stream=True):
     print(part['message']['content'], end='', flush=True)
 
 asyncio.run(chat())
diff --git a/examples/async-chat.py b/examples/async-chat.py
index be10cfc..f3b6f5f 100644
--- a/examples/async-chat.py
+++ b/examples/async-chat.py
@@ -1,6 +1,6 @@
 import asyncio
 
-from ollama import AsyncClient
+import ollama
 
 
 async def main():
@@ -11,7 +11,7 @@ async def main():
     },
   ]
 
-  client = AsyncClient()
+  client = ollama.AsyncClient()
   response = await client.chat('llama3.2', messages=messages)
   print(response['message']['content'])
 
diff --git a/examples/async-structured-outputs.py b/examples/async-structured-outputs.py
index a33c4c9..02c515f 100644
--- a/examples/async-structured-outputs.py
+++ b/examples/async-structured-outputs.py
@@ -2,7 +2,7 @@
 
 from pydantic import BaseModel
 
-from ollama import AsyncClient
+import ollama
 
 
 # Define the schema for the response
@@ -17,7 +17,7 @@ class FriendList(BaseModel):
 
 
 async def main():
-  client = AsyncClient()
+  client = ollama.AsyncClient()
   response = await client.chat(
     model='llama3.1:8b',
     messages=[{'role': 'user', 'content': 'I have two friends. The first is Ollama 22 years old busy saving the world, and the second is Alonso 23 years old and wants to hang out. Return a list of friends in JSON format'}],
diff --git a/examples/async-tools.py b/examples/async-tools.py
index 5578229..5982cee 100644
--- a/examples/async-tools.py
+++ b/examples/async-tools.py
@@ -1,7 +1,6 @@
 import asyncio
 
 import ollama
-from ollama import ChatResponse
 
 
 def add_two_numbers(a: int, b: int) -> int:
@@ -54,7 +53,7 @@ def subtract_two_numbers(a: int, b: int) -> int:
 async def main():
   client = ollama.AsyncClient()
 
-  response: ChatResponse = await client.chat(
+  response: ollama.ChatResponse = await client.chat(
     'llama3.1',
     messages=messages,
     tools=[add_two_numbers, subtract_two_numbers_tool],
diff --git a/examples/chat-stream.py b/examples/chat-stream.py
index 3aed84f..1c0d2d6 100644
--- a/examples/chat-stream.py
+++ b/examples/chat-stream.py
@@ -1,4 +1,4 @@
-from ollama import chat
+import ollama
 
 messages = [
   {
@@ -7,7 +7,7 @@
   },
 ]
 
-for part in chat('llama3.2', messages=messages, stream=True):
+for part in ollama.chat('llama3.2', messages=messages, stream=True):
   print(part['message']['content'], end='', flush=True)
 
 print()
diff --git a/examples/chat-with-history.py b/examples/chat-with-history.py
index 2e0cc1d..82320bd 100644
--- a/examples/chat-with-history.py
+++ b/examples/chat-with-history.py
@@ -1,4 +1,4 @@
-from ollama import chat
+import ollama
 
 messages = [
   {
@@ -21,7 +21,7 @@
 
 while True:
   user_input = input('Chat with history: ')
-  response = chat(
+  response = ollama.chat(
     'llama3.2',
     messages=messages
     + [
diff --git a/examples/chat.py b/examples/chat.py
index 2a30f8a..115ad51 100644
--- a/examples/chat.py
+++ b/examples/chat.py
@@ -1,4 +1,4 @@
-from ollama import chat
+import ollama
 
 messages = [
   {
@@ -7,5 +7,5 @@
   },
 ]
 
-response = chat('llama3.2', messages=messages)
+response = ollama.chat('llama3.2', messages=messages)
 print(response['message']['content'])
diff --git a/examples/create.py b/examples/create.py
index 1c06f05..889a88b 100644
--- a/examples/create.py
+++ b/examples/create.py
@@ -1,6 +1,6 @@
 import sys
 
-from ollama import create
+import ollama
 
 args = sys.argv[1:]
 if len(args) == 2:
@@ -25,5 +25,5 @@
 SYSTEM You are Mario from super mario bros, acting as an assistant.
 """
 
-for response in create(model=args[0], modelfile=modelfile, stream=True):
+for response in ollama.create(model=args[0], modelfile=modelfile, stream=True):
   print(response['status'])
diff --git a/examples/embed.py b/examples/embed.py
index 5af145e..a53c8da 100644
--- a/examples/embed.py
+++ b/examples/embed.py
@@ -1,4 +1,4 @@
-from ollama import embed
+import ollama
 
-response = embed(model='llama3.2', input='Hello, world!')
+response = ollama.embed(model='llama3.2', input='Hello, world!')
 print(response['embeddings'])
diff --git a/examples/fill-in-middle.py b/examples/fill-in-middle.py
index 0bd2e01..447ff0b 100644
--- a/examples/fill-in-middle.py
+++ b/examples/fill-in-middle.py
@@ -1,4 +1,4 @@
-from ollama import generate
+import ollama
 
 prompt = '''def remove_non_ascii(s: str) -> str:
     """ '''
@@ -7,7 +7,7 @@
     return result
 """
 
-response = generate(
+response = ollama.generate(
   model='codellama:7b-code',
   prompt=prompt,
   suffix=suffix,
diff --git a/examples/generate-stream.py b/examples/generate-stream.py
index 698a961..4c29ec0 100644
--- a/examples/generate-stream.py
+++ b/examples/generate-stream.py
@@ -1,4 +1,4 @@
-from ollama import generate
+import ollama
 
-for part in generate('llama3.2', 'Why is the sky blue?', stream=True):
+for part in ollama.generate('llama3.2', 'Why is the sky blue?', stream=True):
   print(part['response'], end='', flush=True)
diff --git a/examples/generate.py b/examples/generate.py
index 7a94de4..56903e3 100644
--- a/examples/generate.py
+++ b/examples/generate.py
@@ -1,4 +1,4 @@
-from ollama import generate
+import ollama
 
-response = generate('llama3.2', 'Why is the sky blue?')
+response = ollama.generate('llama3.2', 'Why is the sky blue?')
 print(response['response'])
diff --git a/examples/list.py b/examples/list.py
index 00d6243..284b2e0 100644
--- a/examples/list.py
+++ b/examples/list.py
@@ -1,8 +1,6 @@
-from ollama import ListResponse, list
+import ollama
 
-response: ListResponse = list()
-
-for model in response.models:
+for model in ollama.list().models:
   print('Name:', model.model)
   print('  Size (MB):', f'{(model.size.real / 1024 / 1024):.2f}')
   if model.details:
diff --git a/examples/multimodal-chat.py b/examples/multimodal-chat.py
index c1a1859..6d2fe30 100644
--- a/examples/multimodal-chat.py
+++ b/examples/multimodal-chat.py
@@ -1,4 +1,4 @@
-from ollama import chat
+import ollama
 
 # from pathlib import Path
 
@@ -10,7 +10,7 @@
 # or the raw bytes
 # img = Path(path).read_bytes()
 
-response = chat(
+response = ollama.chat(
   model='llama3.2-vision',
   messages=[
     {
diff --git a/examples/multimodal-generate.py b/examples/multimodal-generate.py
index 643e9aa..28ff3a3 100644
--- a/examples/multimodal-generate.py
+++ b/examples/multimodal-generate.py
@@ -3,7 +3,7 @@
 
 import httpx
 
-from ollama import generate
+import ollama
 
 latest = httpx.get('https://xkcd.com/info.0.json')
 latest.raise_for_status()
@@ -23,7 +23,7 @@
 raw = httpx.get(comic.json().get('img'))
 raw.raise_for_status()
 
-for response in generate('llava', 'explain this comic:', images=[raw.content], stream=True):
+for response in ollama.generate('llava', 'explain this comic:', images=[raw.content], stream=True):
   print(response['response'], end='', flush=True)
 
 print()
diff --git a/examples/ps.py b/examples/ps.py
index 5f6965c..3871f74 100644
--- a/examples/ps.py
+++ b/examples/ps.py
@@ -1,9 +1,8 @@
-from ollama import ProcessResponse, chat, ps, pull
+import ollama
 
 # Ensure at least one model is loaded
-response = pull('llama3.2', stream=True)
 progress_states = set()
-for progress in response:
+for progress in ollama.pull('llama3.2', stream=True):
   if progress.get('status') in progress_states:
     continue
   progress_states.add(progress.get('status'))
@@ -12,11 +11,9 @@
 print('\n')
 
 print('Waiting for model to load... \n')
-chat(model='llama3.2', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
+ollama.chat(model='llama3.2', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
 
-
-response: ProcessResponse = ps()
-for model in response.models:
+for model in ollama.ps().models:
   print('Model: ', model.model)
   print('  Digest: ', model.digest)
   print('  Expires at: ', model.expires_at)
diff --git a/examples/pull.py b/examples/pull.py
index bd08c54..7e59c4c 100644
--- a/examples/pull.py
+++ b/examples/pull.py
@@ -1,9 +1,9 @@
 from tqdm import tqdm
 
-from ollama import pull
+import ollama
 
 current_digest, bars = '', {}
-for progress in pull('llama3.2', stream=True):
+for progress in ollama.pull('llama3.2', stream=True):
   digest = progress.get('digest', '')
   if digest != current_digest and current_digest in bars:
     bars[current_digest].close()
diff --git a/examples/structured-outputs-image.py b/examples/structured-outputs-image.py
index 722a252..a7d4f56 100644
--- a/examples/structured-outputs-image.py
+++ b/examples/structured-outputs-image.py
@@ -3,7 +3,7 @@
 
 from pydantic import BaseModel
 
-from ollama import chat
+import ollama
 
 
 # Define the schema for image objects
@@ -32,7 +32,7 @@ class ImageDescription(BaseModel):
   raise FileNotFoundError(f'Image not found at: {path}')
 
 # Set up chat as usual
-response = chat(
+response = ollama.chat(
   model='llama3.2-vision',
   format=ImageDescription.model_json_schema(),  # Pass in the schema for the response
   messages=[
diff --git a/examples/structured-outputs.py b/examples/structured-outputs.py
index 4c60d5f..932e273 100644
--- a/examples/structured-outputs.py
+++ b/examples/structured-outputs.py
@@ -1,6 +1,6 @@
 from pydantic import BaseModel
 
-from ollama import chat
+import ollama
 
 
 # Define the schema for the response
@@ -15,7 +15,7 @@ class FriendList(BaseModel):
 
 
 # schema = {'type': 'object', 'properties': {'friends': {'type': 'array', 'items': {'type': 'object', 'properties': {'name': {'type': 'string'}, 'age': {'type': 'integer'}, 'is_available': {'type': 'boolean'}}, 'required': ['name', 'age', 'is_available']}}}, 'required': ['friends']}
-response = chat(
+response = ollama.chat(
   model='llama3.1:8b',
   messages=[{'role': 'user', 'content': 'I have two friends. The first is Ollama 22 years old busy saving the world, and the second is Alonso 23 years old and wants to hang out. Return a list of friends in JSON format'}],
   format=FriendList.model_json_schema(),  # Use Pydantic to generate the schema or format=schema
diff --git a/examples/tools.py b/examples/tools.py
index 32a2012..bc000da 100644
--- a/examples/tools.py
+++ b/examples/tools.py
@@ -1,4 +1,4 @@
-from ollama import ChatResponse, chat
+import ollama
 
 
 def add_two_numbers(a: int, b: int) -> int:
@@ -47,7 +47,7 @@ def subtract_two_numbers(a: int, b: int) -> int:
   'subtract_two_numbers': subtract_two_numbers,
 }
 
-response: ChatResponse = chat(
+response: ollama.ChatResponse = ollama.chat(
   'llama3.1',
   messages=messages,
   tools=[add_two_numbers, subtract_two_numbers_tool],
@@ -72,7 +72,7 @@ def subtract_two_numbers(a: int, b: int) -> int:
   messages.append({'role': 'tool', 'content': str(output), 'name': tool.function.name})
 
   # Get final response from model with function outputs
-  final_response = chat('llama3.1', messages=messages)
+  final_response = ollama.chat('llama3.1', messages=messages)
   print('Final response:', final_response.message.content)
 
 else: