mirror of
https://github.com/nomic-ai/gpt4all
synced 2024-11-02 09:40:42 +00:00
48 lines
903 B
Markdown
48 lines
903 B
Markdown
# Python GPT4All
|
|
|
|
This package contains a set of Python bindings around the `llmodel` C-API.
|
|
|
|
## Documentation
|
|
docs.gpt4all.io
|
|
|
|
## Installation
|
|
|
|
```
|
|
pip install gpt4all
|
|
```
|
|
|
|
## Local Build Instructions
|
|
|
|
**NOTE**: If you are doing this on a Windows machine, you must build the GPT4All backend using [MinGW64](https://www.mingw-w64.org/) compiler.
|
|
|
|
1. Setup `llmodel`
|
|
|
|
```
|
|
git clone --recurse-submodules https://github.com/nomic-ai/gpt4all
|
|
cd gpt4all/gpt4all-backend/
|
|
mkdir build
|
|
cd build
|
|
cmake ..
|
|
cmake --build . --parallel
|
|
```
|
|
Confirm that `libllmodel.*` exists in `gpt4all-backend/build`.
|
|
|
|
2. Setup Python package
|
|
|
|
```
|
|
cd ../../gpt4all-bindings/python
|
|
pip3 install -e .
|
|
```
|
|
|
|
3. Test it out! In a Python script or console:
|
|
|
|
```python
|
|
|
|
from gpt4all import GPT4All
|
|
|
|
gptj = GPT4All("ggml-gpt4all-j-v1.3-groovy")
|
|
messages = [{"role": "user", "content": "Name 3 colors"}]
|
|
gptj.chat_completion(messages)
|
|
|
|
```
|