obscura/ollama-python
1
0
Fork 0
mirror of https://github.com/ollama/ollama-python.git synced 2026-10-15 21:37:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #138 from TitanStar73/patch-1

Browse Source 
Update README.md
This commit is contained in:
Michael Yang
2024-05-08 13:13:06 -07:00
committed by GitHub
parent 2b66adebef e5c4799650
commit a8cb34e0ec
1 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+14 -14
View File
@@ -30,7 +30,7 @@ pip install ollama
```python ```python
import ollama import ollama
response = ollama.chat(model='llama2', messages=[ response = ollama.chat(model='llama3', messages=[
{ {
'role': 'user', 'role': 'user',
'content': 'Why is the sky blue?', 'content': 'Why is the sky blue?',
@@ -47,7 +47,7 @@ Response streaming can be enabled by setting `stream=True`, modifying function c
import ollama import ollama
stream = ollama.chat( stream = ollama.chat(
model='llama2', model='llama3',
messages=[{'role': 'user', 'content': 'Why is the sky blue?'}], messages=[{'role': 'user', 'content': 'Why is the sky blue?'}],
stream=True, stream=True,
) )
@@ -63,13 +63,13 @@ The Ollama Python library's API is designed around the [Ollama REST API](https:/
### Chat ### Chat
```python ```python
ollama.chat(model='llama2', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}]) ollama.chat(model='llama3', messages=[{'role': 'user', 'content': 'Why is the sky blue?'}])
``` ```
### Generate ### Generate
```python ```python
ollama.generate(model='llama2', prompt='Why is the sky blue?') ollama.generate(model='llama3', prompt='Why is the sky blue?')
``` ```
### List ### List
@@ -81,14 +81,14 @@ ollama.list()
### Show ### Show
```python ```python
ollama.show('llama2') ollama.show('llama3')
``` ```
### Create ### Create
```python ```python
modelfile=''' modelfile='''
FROM llama2 FROM llama3
SYSTEM You are mario from super mario bros. SYSTEM You are mario from super mario bros.
''' '''
@@ -98,31 +98,31 @@ ollama.create(model='example', modelfile=modelfile)
### Copy ### Copy
```python ```python
ollama.copy('llama2', 'user/llama2') ollama.copy('llama3', 'user/llama3')
``` ```
### Delete ### Delete
```python ```python
ollama.delete('llama2') ollama.delete('llama3')
``` ```
### Pull ### Pull
```python ```python
ollama.pull('llama2') ollama.pull('llama3')
``` ```
### Push ### Push
```python ```python
ollama.push('user/llama2') ollama.push('user/llama3')
``` ```
### Embeddings ### Embeddings
```python ```python
ollama.embeddings(model='llama2', prompt='The sky is blue because of rayleigh scattering') ollama.embeddings(model='llama3', prompt='The sky is blue because of rayleigh scattering')
``` ```
## Custom client ## Custom client
@@ -135,7 +135,7 @@ A custom client can be created with the following fields:
```python ```python
from ollama import Client from ollama import Client
client = Client(host='http://localhost:11434') client = Client(host='http://localhost:11434')
response = client.chat(model='llama2', messages=[ response = client.chat(model='llama3', messages=[
{ {
'role': 'user', 'role': 'user',
'content': 'Why is the sky blue?', 'content': 'Why is the sky blue?',
@@ -151,7 +151,7 @@ from ollama import AsyncClient
async def chat(): async def chat():
message = {'role': 'user', 'content': 'Why is the sky blue?'} message = {'role': 'user', 'content': 'Why is the sky blue?'}
response = await AsyncClient().chat(model='llama2', messages=[message]) response = await AsyncClient().chat(model='llama3', messages=[message])
asyncio.run(chat()) asyncio.run(chat())
``` ```
@@ -164,7 +164,7 @@ from ollama import AsyncClient
async def chat(): async def chat():
message = {'role': 'user', 'content': 'Why is the sky blue?'} message = {'role': 'user', 'content': 'Why is the sky blue?'}
async for part in await AsyncClient().chat(model='llama2', messages=[message], stream=True): async for part in await AsyncClient().chat(model='llama3', messages=[message], stream=True):
print(part['message']['content'], end='', flush=True) print(part['message']['content'], end='', flush=True)
asyncio.run(chat()) asyncio.run(chat())