From 3368924229cbb9bde0a5ef86b3533d1cf829f996 Mon Sep 17 00:00:00 2001 From: Richard Guo Date: Thu, 11 May 2023 11:02:44 -0400 Subject: [PATCH] documentation and cleanup --- gpt4all-bindings/python/README.md | 7 ++-- gpt4all-bindings/python/docs/index.md | 16 +++++++-- gpt4all-bindings/python/gpt4all/gpt4all.py | 40 ++++++++++++++++------ gpt4all-bindings/python/mkdocs.yml | 7 +--- gpt4all-bindings/python/setup.py | 2 +- 5 files changed, 46 insertions(+), 26 deletions(-) diff --git a/gpt4all-bindings/python/README.md b/gpt4all-bindings/python/README.md index 057704d1..f006b7ea 100644 --- a/gpt4all-bindings/python/README.md +++ b/gpt4all-bindings/python/README.md @@ -1,11 +1,9 @@ # Python GPT4All -This package contains a set of Python bindings that runs the `llmodel` C-API. +This package contains a set of Python bindings around the `llmodel` C-API. -# Local Installation Instructions - -TODO: Right now instructions in main README still depend on Qt6 setup. To setup Python bindings, we just need `llmodel` to be built which is much simpler. However, in the future, the below installation instructions should be sequentially organized such that we expect the main README's instructions were followed first. +## Local Build Instructions 1. Setup `llmodel` @@ -23,7 +21,6 @@ Confirm that `libllmodel.*` exists in `gpt4all-backend/llmodel/build`. ``` cd ../../gpt4all-bindings/python -pip3 install -r requirements.txt pip3 install -e . ``` diff --git a/gpt4all-bindings/python/docs/index.md b/gpt4all-bindings/python/docs/index.md index 1e5dabd2..788daf8d 100644 --- a/gpt4all-bindings/python/docs/index.md +++ b/gpt4all-bindings/python/docs/index.md @@ -1,6 +1,6 @@ # GPT4All -In this package, we introduce Python bindings built around GPT4All's C/C++ ecosystem. +In this package, we introduce Python bindings built around GPT4All's C/C++ model backends. ## Quickstart @@ -11,7 +11,7 @@ pip install gpt4all In Python, run the following commands to retrieve a GPT4All model and generate a response to a prompt. -**Download Note*:* +**Download Note*:** By default, models are stored in `~/.cache/gpt4all/` (you can change this with `model_path`). If the file already exists, model download will be skipped. ```python @@ -19,4 +19,14 @@ import gpt4all gptj = gpt4all.GPT4All("ggml-gpt4all-j-v1.3-groovy") messages = [{"role": "user", "content": "Name 3 colors"}] gptj.chat_completion(messages) -``` \ No newline at end of file +``` + +## Give it a try! +[Google Colab Tutorial](https://colab.research.google.com/drive/1QRFHV5lj1Kb7_tGZZGZ-E6BfX6izpeMI?usp=sharing) + + +## Best Practices +GPT4All models are designed to run locally on your own CPU. Large prompts may require longer computation time and +result in worse performance. Giving an instruction to the model will typically produce the best results. + +There are two methods to interface with the underlying language model, `chat_completion()` and `generate()`. Chat completion formats a user-provided message dictionary into a prompt template (see API documentation for more details and options). This will usually produce much better results and is the approach we recommend. You may also prompt the model with `generate()` which will just pass the raw input string to the model. \ No newline at end of file diff --git a/gpt4all-bindings/python/gpt4all/gpt4all.py b/gpt4all-bindings/python/gpt4all/gpt4all.py index 7e93a3b0..2b901251 100644 --- a/gpt4all-bindings/python/gpt4all/gpt4all.py +++ b/gpt4all-bindings/python/gpt4all/gpt4all.py @@ -15,7 +15,7 @@ from . import pyllmodel DEFAULT_MODEL_DIRECTORY = os.path.join(str(Path.home()), ".cache", "gpt4all").replace("\\", "\\\\") class GPT4All(): - """Python API for retrieving and interacting with GPT4All models + """Python API for retrieving and interacting with GPT4All models. Attribuies: model: Pointer to underlying C model. @@ -50,7 +50,7 @@ class GPT4All(): @staticmethod def list_models(): """ - Fetch model list from https://gpt4all.io/models/models.json + Fetch model list from https://gpt4all.io/models/models.json. Returns: Model list in JSON format. @@ -60,7 +60,7 @@ class GPT4All(): return model_json @staticmethod - def retrieve_model(model_name: str, model_path: str = None, allow_download = True): + def retrieve_model(model_name: str, model_path: str = None, allow_download: bool = True) -> str: """ Find model file, and if it doesn't exist, download the model. @@ -113,8 +113,18 @@ class GPT4All(): raise ValueError("Invalid model directory") @staticmethod - def download_model(model_filename, model_path): - # TODO: Find good way of safely removing file that got interrupted. + def download_model(model_filename: str, model_path: str) -> str: + """ + Download model from https://gpt4all.io. + + Args: + model_filename: Filename of model (with .bin extension). + model_path: Path to download model to. + + Returns: + Model file destination. + """ + def get_download_url(model_filename): return f"https://gpt4all.io/models/{model_filename}" @@ -122,6 +132,7 @@ class GPT4All(): download_path = os.path.join(model_path, model_filename).replace("\\", "\\\\") download_url = get_download_url(model_filename) + # TODO: Find good way of safely removing file that got interrupted. response = requests.get(download_url, stream=True) total_size_in_bytes = int(response.headers.get("content-length", 0)) block_size = 1048576 # 1 MB @@ -141,9 +152,16 @@ class GPT4All(): print("Model downloaded at: " + download_path) return download_path - def generate(self, prompt: str, **generate_kwargs): + def generate(self, prompt: str, **generate_kwargs) -> str: """ Surfaced method of running generate without accessing model object. + + Args: + prompt: Raw string to be passed to model. + **generate_kwargs: Optional kwargs to pass to prompt context. + + Returns: + Raw string of generated model response. """ return self.model.generate(prompt, **generate_kwargs) @@ -158,13 +176,13 @@ class GPT4All(): generated content. Args: - messages: Each dictionary should have a "role" key + messages: List of dictionaries. Each dictionary should have a "role" key with value of "system", "assistant", or "user" and a "content" key with a string value. Messages are organized such that "system" messages are at top of prompt, and "user" and "assistant" messages are displayed in order. Assistant messages get formatted as "Reponse: {content}". - default_prompt_header: If True (default), add default prompt header after any user specified system messages and - before user/assistant messages. + default_prompt_header: If True (default), add default prompt header after any system role messages and + before user/assistant role messages. default_prompt_footer: If True (default), add default footer at end of prompt. verbose: If True (default), print full prompt and generated response. @@ -175,7 +193,6 @@ class GPT4All(): generated tokens in response, and total tokens. "choices": List of message dictionary where "content" is generated response and "role" is set as "assistant". Right now, only one choice is returned by model. - """ full_prompt = self._build_prompt(messages, @@ -210,6 +227,7 @@ class GPT4All(): def _build_prompt(messages: List[Dict], default_prompt_header=True, default_prompt_footer=False) -> str: + # Helper method to format messages into prompt. full_prompt = "" for message in messages: @@ -238,7 +256,7 @@ class GPT4All(): @staticmethod def get_model_from_type(model_type: str) -> pyllmodel.LLModel: - # This needs to be updated for each new model + # This needs to be updated for each new model type # TODO: Might be worth converting model_type to enum if model_type == "gptj": diff --git a/gpt4all-bindings/python/mkdocs.yml b/gpt4all-bindings/python/mkdocs.yml index 2175bec0..b5ecdcc4 100644 --- a/gpt4all-bindings/python/mkdocs.yml +++ b/gpt4all-bindings/python/mkdocs.yml @@ -68,9 +68,4 @@ extra: generator: false analytics: provider: google - property: G-NPXC8BYHJV - #social: - # - icon: fontawesome/brands/twitter - # link: https://twitter.com/nomic_ai - # - icon: material/fruit-pineapple - # link: https://www.youtube.com/watch?v=628eVJgHD6I \ No newline at end of file + property: G-NPXC8BYHJV \ No newline at end of file diff --git a/gpt4all-bindings/python/setup.py b/gpt4all-bindings/python/setup.py index 3d0f335b..35e403a1 100644 --- a/gpt4all-bindings/python/setup.py +++ b/gpt4all-bindings/python/setup.py @@ -61,7 +61,7 @@ copy_prebuilt_C_lib(SRC_CLIB_DIRECtORY, setup( name=package_name, - version="0.1.9", + version="0.2.0", description="Python bindings for GPT4All", author="Richard Guo", author_email="richard@nomic.ai",