No project description provided
Project description
Ollama Python Library
The ollama python library provides the easiest way to integrate your python project with Ollama
Getting Started
This requires a python version of 3.9 or higher
pip install ollama-python
The python package splits the functionality into three core endpoints
- Model Management Endpoints: This includes the ability to create, delete, pull, push and list models amongst others
- Generate Endpoint: This includes the generate and chat endpoints in Ollama
- Embedding Endpoint: This includes the ability to generate embeddings for a given text
Pydantic is used to verify user input and Responses from the server are parsed into pydantic models
Example Usage
Generate Endpoint
Completions (Generate)
Without Streaming
from ollama_python.endpoints import GenerateAPI
api = GenerateAPI(base_url="http://localhost:8000", model="mistral")
result = api.generate(prompt="Hello World", options=dict(num_tokens=10), format="json")
With Streaming
from ollama_python.endpoints import GenerateAPI
api = GenerateAPI(base_url="http://localhost:8000", model="mistral")
for res in api.generate(prompt="Hello World", options=dict(num_tokens=10), format="json", stream=True):
print(res.response)
Chat Completions
Without Streaming
from ollama_python.endpoints import GenerateAPI
api = GenerateAPI(base_url="http://localhost:8000", model="mistral")
messages = [{'role': 'user', 'content': 'Why is the sky blue?'}]
result = api.generate_chat_completion(messages=messages, options=dict(num_tokens=10), format="json")
With Streaming
from ollama_python.endpoints import GenerateAPI
api = GenerateAPI(base_url="http://localhost:8000", model="mistral")
messages = [{'role': 'user', 'content': 'Why is the sky blue?'}]
for res in api.generate_chat_completion(messages=messages, options=dict(num_tokens=10), format="json", stream=True):
print(res.message)
Chat request with images
from ollama_python.endpoints import GenerateAPI
api = GenerateAPI(base_url="http://localhost:8000", model="llava")
messages = [{'role': 'user', 'content': 'What is in this image', 'image': 'iVBORw0KGgoAAAANSUhEUgAAAG0AAABmCAYAAADBPx+VAAAACXBIWXMAAAsTAAALEwEAmp'}]
result = api.generate_chat_completion(messages=messages, options=dict(num_tokens=10), format="json")
print(result.message)
Embeddings Endpoint
Generate Embeddings
from ollama_python.endpoints import EmbeddingAPI
api = EmbeddingAPI(base_url="http://localhost:8000", model="mistral")
result = api.get_embedding(prompt="Hello World", options=dict(seed=10))
Model Management Endpoints
Create a model
Without Streaming
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
result = api.create(name="test_model", model_file="random model_file")
With Streaming
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
for res in api.create(name="test_model", model_file="random model_file", stream=True):
print(res.status)
Check if a blob exists
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
result = api.check_blob_exists(digest="sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2")
Create a blob
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
result = api.create_blob(digest="sha256:29fdb92e57cf0827ded04ae6461b5931d01fa595843f55d36f5b275a52087dd2")
List local models
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
result = api.list_local_models()
print(result.models)
Show model information
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
result = api.show(name="mistral")
print(result.details)
Copy a model
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
result = api.copy(source="mistral", destination="mistral_copy")
Delete a model
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
api.delete(name="mistral_copy")
Pull a model
Without Streaming
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
result = api.pull(name="mistral")
print(result.status)
With Streaming
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
for res in api.pull(name="mistral", stream=True):
print(res.status)
Push a model
Without Streaming
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
result = api.push(name="mistral")
print(result.status)
With Streaming
from ollama_python.endpoints import ModelManagementAPI
api = ModelManagementAPI(base_url="http://localhost:8000")
for res in api.push(name="mistral", stream=True):
print(res.status)
Valid Options/Parameters
Parameter | Description | Value Type | Example Usage |
---|---|---|---|
mirostat | Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0) | int | mirostat 0 |
mirostat_eta | Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1) | float | mirostat_eta 0.1 |
mirostat_tau | Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0) | float | mirostat_tau 5.0 |
num_ctx | Sets the size of the context window used to generate the next token. (Default: 2048) | int | num_ctx 4096 |
num_gqa | The number of GQA groups in the transformer layer. Required for some models, for example it is 8 for llama2:70b | int | num_gqa 1 |
num_gpu | The number of layers to send to the GPU(s). On macOS it defaults to 1 to enable metal support, 0 to disable. | int | num_gpu 50 |
num_thread | Sets the number of threads to use during computation. By default, Ollama will detect this for optimal performance. It is recommended to set this value to the number of physical CPU cores your system has (as opposed to the logical number of cores). | int | num_thread 8 |
repeat_last_n | Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx) | int | repeat_last_n 64 |
repeat_penalty | Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1) | float | repeat_penalty 1.1 |
temperature | The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8) | float | temperature 0.7 |
seed | Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0) | int | seed 42 |
stop | Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile. |
string | stop "AI assistant:" |
tfs_z | Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1) | float | tfs_z 1 |
num_predict | Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context) | int | num_predict 42 |
top_k | Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40) | int | top_k 40 |
top_p | Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9) | float | top_p 0.9 |
Todo
Add support for Asynchronous version of the library
To Contribute
- Clone the repo
- Run
poetry install
- Run
pre-commit install
Then you're ready to contribute to the repo
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ollama_python-0.1.2.tar.gz
(14.1 kB
view details)
Built Distribution
File details
Details for the file ollama_python-0.1.2.tar.gz
.
File metadata
- Download URL: ollama_python-0.1.2.tar.gz
- Upload date:
- Size: 14.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.18
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 85161427858a77603bf035e1d7acefcd330d656a9b95bae79c5f55cced3b3e30 |
|
MD5 | ad147646c0ba362d3f435af0e57fa375 |
|
BLAKE2b-256 | 1ace4b706a333f1dbf0cea1745e121b135f8df378f9ea6df019de2eedadf40ef |
File details
Details for the file ollama_python-0.1.2-py3-none-any.whl
.
File metadata
- Download URL: ollama_python-0.1.2-py3-none-any.whl
- Upload date:
- Size: 16.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.18
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0b0d2fcd97d823a424446c02febb7c7f7188287c01e5ee7210d0e42ca928644a |
|
MD5 | c703789da81d7f919fe04791ddcc7d36 |
|
BLAKE2b-256 | bcd3552575843a7e475f6a3a573ccdcac0a9046e03330e29d0416d3d5cc7d5ba |