readme: update to use gemma 4 and format (#740)

README.md

@@ -5,7 +5,7 @@ The Ollama Python library provides the easiest way to integrate Python 3.8+ proj
 ## Prerequisites
 
 - [Ollama](https://ollama.com/download) should be installed and running
-- Pull a model to use with the library: `ollama pull <model>` e.g. `ollama pull gemma3`
+- Pull a model to use with the library: `ollama pull <model>` e.g. `ollama pull gemma4`
   - See [Ollama.com](https://ollama.com/search) for more information on the models available.
 
 ## Install
@@ -20,12 +20,15 @@ pip install ollama
 from ollama import chat
 from ollama import ChatResponse
 
-response: ChatResponse = chat(model='gemma3', messages=[
+response: ChatResponse = chat(
-  {
+  model='gemma4',
-    'role': 'user',
+  messages=[
-    'content': 'Why is the sky blue?',
+    {
-  },
+      'role': 'user',
-])
+      'content': 'Why is the sky blue?',
+    },
+  ],
+)
 print(response['message']['content'])
 # or access fields directly from the response object
 print(response.message.content)
@@ -41,9 +44,9 @@ Response streaming can be enabled by setting `stream=True`.
 from ollama import chat
 
 stream = chat(
-    model='gemma3',
+  model='gemma4',
-    messages=[{'role': 'user', 'content': 'Why is the sky blue?'}],
+  messages=[{'role': 'user', 'content': 'Why is the sky blue?'}],
-    stream=True,
+  stream=True,
 )
 
 for chunk in stream:
@@ -110,10 +113,7 @@ curl https://ollama.com/api/tags
 import os
 from ollama import Client
 
-client = Client(
+client = Client(host='https://ollama.com', headers={'Authorization': 'Bearer ' + os.environ.get('OLLAMA_API_KEY')})
-    host='https://ollama.com',
-    headers={'Authorization': 'Bearer ' + os.environ.get('OLLAMA_API_KEY')}
-)
 
 messages = [
   {
@@ -133,16 +133,17 @@ All extra keyword arguments are passed into the [`httpx.Client`](https://www.pyt
 
 ```python
 from ollama import Client
-client = Client(
+
-  host='http://localhost:11434',
+client = Client(host='http://localhost:11434', headers={'x-some-header': 'some-value'})
-  headers={'x-some-header': 'some-value'}
+response = client.chat(
+  model='gemma4',
+  messages=[
+    {
+      'role': 'user',
+      'content': 'Why is the sky blue?',
+    },
+  ],
 )
-response = client.chat(model='gemma3', messages=[
-  {
-    'role': 'user',
-    'content': 'Why is the sky blue?',
-  },
-])
 ```
 
 ## Async client
@@ -153,9 +154,11 @@ The `AsyncClient` class is used to make asynchronous requests. It can be configu
 import asyncio
 from ollama import AsyncClient
 
+
 async def chat():
   message = {'role': 'user', 'content': 'Why is the sky blue?'}
-  response = await AsyncClient().chat(model='gemma3', messages=[message])
+  response = await AsyncClient().chat(model='gemma4', messages=[message])
+
 
 asyncio.run(chat())
 ```
@@ -166,11 +169,13 @@ Setting `stream=True` modifies functions to return a Python asynchronous generat
 import asyncio
 from ollama import AsyncClient
 
+
 async def chat():
   message = {'role': 'user', 'content': 'Why is the sky blue?'}
-  async for part in await AsyncClient().chat(model='gemma3', messages=[message], stream=True):
+  async for part in await AsyncClient().chat(model='gemma4', messages=[message], stream=True):
     print(part['message']['content'], end='', flush=True)
 
+
 asyncio.run(chat())
 ```
 
@@ -181,13 +186,13 @@ The Ollama Python library's API is designed around the [Ollama REST API](https:/
 ### Chat
 
 ```python
-ollama.chat(model='gemma3', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
+ollama.chat(model='gemma4', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
 ```
 
 ### Generate
 
 ```python
-ollama.generate(model='gemma3', prompt='Why is the sky blue?')
+ollama.generate(model='gemma4', prompt='Why is the sky blue?')
 ```
 
 ### List
@@ -199,49 +204,49 @@ ollama.list()
 ### Show
 
 ```python
-ollama.show('gemma3')
+ollama.show('gemma4')
 ```
 
 ### Create
 
 ```python
-ollama.create(model='example', from_='gemma3', system="You are Mario from Super Mario Bros.")
+ollama.create(model='example', from_='gemma4', system='You are Mario from Super Mario Bros.')
 ```
 
 ### Copy
 
 ```python
-ollama.copy('gemma3', 'user/gemma3')
+ollama.copy('gemma4', 'user/gemma4')
 ```
 
 ### Delete
 
 ```python
-ollama.delete('gemma3')
+ollama.delete('gemma4')
 ```
 
 ### Pull
 
 ```python
-ollama.pull('gemma3')
+ollama.pull('gemma4')
 ```
 
 ### Push
 
 ```python
-ollama.push('user/gemma3')
+ollama.push('user/gemma4')
 ```
 
 ### Embed
 
 ```python
-ollama.embed(model='gemma3', input='The sky is blue because of rayleigh scattering')
+ollama.embed(model='gemma4', input='The sky is blue because of rayleigh scattering')
 ```
 
 ### Embed (batch)
 
 ```python
-ollama.embed(model='gemma3', input=['The sky is blue because of rayleigh scattering', 'Grass is green because of chlorophyll'])
+ollama.embed(model='gemma4', input=['The sky is blue because of rayleigh scattering', 'Grass is green because of chlorophyll'])
 ```
 
 ### Ps

examples/async-chat.py

@@ -12,7 +12,7 @@ async def main():
   ]
 
   client = AsyncClient()
-  response = await client.chat('gemma3', messages=messages)
+  response = await client.chat('gemma4', messages=messages)
   print(response['message']['content'])
 
 

examples/async-generate.py

@@ -5,7 +5,7 @@ import ollama
 
 async def main():
   client = ollama.AsyncClient()
-  response = await client.generate('gemma3', 'Why is the sky blue?')
+  response = await client.generate('gemma4', 'Why is the sky blue?')
   print(response['response'])
 
 

examples/chat-logprobs.py

@@ -22,7 +22,7 @@ messages = [
 ]
 
 response = ollama.chat(
-  model='gemma3',
+  model='gemma4',
   messages=messages,
   logprobs=True,
   top_logprobs=3,

examples/chat-stream.py

@@ -7,5 +7,5 @@ messages = [
   },
 ]
 
-for part in chat('gemma3', messages=messages, stream=True):
+for part in chat('gemma4', messages=messages, stream=True):
   print(part['message']['content'], end='', flush=True)

examples/chat-with-history.py

@@ -23,7 +23,7 @@ messages = [
 while True:
   user_input = input('Chat with history: ')
   response = chat(
-    'gemma3',
+    'gemma4',
     messages=[*messages, {'role': 'user', 'content': user_input}],
   )
 

examples/chat.py

@@ -7,5 +7,5 @@ messages = [
   },
 ]
 
-response = chat('gemma3', messages=messages)
+response = chat('gemma4', messages=messages)
 print(response['message']['content'])

examples/create.py

@@ -3,7 +3,7 @@ from ollama import Client
 client = Client()
 response = client.create(
   model='my-assistant',
-  from_='gemma3',
+  from_='gemma4',
   system='You are mario from Super Mario Bros.',
   stream=False,
 )

examples/generate-logprobs.py

@@ -15,7 +15,7 @@ def print_logprobs(logprobs: Iterable[dict], label: str) -> None:
 
 
 response = ollama.generate(
-  model='gemma3',
+  model='gemma4',
   prompt='hi! be concise.',
   logprobs=True,
   top_logprobs=3,

examples/generate-stream.py

@@ -1,4 +1,4 @@
 from ollama import generate
 
-for part in generate('gemma3', 'Why is the sky blue?', stream=True):
+for part in generate('gemma4', 'Why is the sky blue?', stream=True):
   print(part['response'], end='', flush=True)

examples/generate.py

@@ -1,4 +1,4 @@
 from ollama import generate
 
-response = generate('gemma3', 'Why is the sky blue?')
+response = generate('gemma4', 'Why is the sky blue?')
 print(response['response'])

examples/multimodal-chat.py

@@ -11,7 +11,7 @@ path = input('Please enter the path to the image: ')
 # img = Path(path).read_bytes()
 
 response = chat(
-  model='gemma3',
+  model='gemma4',
   messages=[
     {
       'role': 'user',

examples/ps.py

@@ -1,7 +1,7 @@
 from ollama import ProcessResponse, chat, ps, pull
 
 # Ensure at least one model is loaded
-response = pull('gemma3', stream=True)
+response = pull('gemma4', stream=True)
 progress_states = set()
 for progress in response:
   if progress.get('status') in progress_states:
@@ -12,7 +12,7 @@ for progress in response:
 print('\n')
 
 print('Waiting for model to load... \n')
-chat(model='gemma3', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
+chat(model='gemma4', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
 
 
 response: ProcessResponse = ps()

examples/pull.py

@@ -3,7 +3,7 @@ from tqdm import tqdm
 from ollama import pull
 
 current_digest, bars = '', {}
-for progress in pull('gemma3', stream=True):
+for progress in pull('gemma4', stream=True):
   digest = progress.get('digest', '')
   if digest != current_digest and current_digest in bars:
     bars[current_digest].close()

examples/show.py

@@ -1,6 +1,6 @@
 from ollama import ShowResponse, show
 
-response: ShowResponse = show('gemma3')
+response: ShowResponse = show('gemma4')
 print('Model Information:')
 print(f'Modified at:   {response.modified_at}')
 print(f'Template:      {response.template}')

examples/structured-outputs-image.py

@@ -33,7 +33,7 @@ if not path.exists():
 
 # Set up chat as usual
 response = chat(
-  model='gemma3',
+  model='gemma4',
   format=ImageDescription.model_json_schema(),  # Pass in the schema for the response
   messages=[
     {