mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-02 09:40:26 +00:00
[Breaking] Migrate GPT4All to use PyGPT4All (#3934)
Seems the pyllamacpp package is no longer the supported bindings from gpt4all. Tested that this works locally. Given that the older models weren't very performant, I think it's better to migrate now without trying to include a lot of try / except blocks --------- Co-authored-by: Nissan Pow <npow@users.noreply.github.com> Co-authored-by: Nissan Pow <pownissa@amazon.com>
This commit is contained in:
Zander Chase
GitHub
parent
f0a4bbb8e2
commit
c4cb55a0c5
@ -1,173 +1,173 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# GPT4All\n",
|
||||
"\n",
|
||||
"[GitHub:nomic-ai/gpt4all](https://github.com/nomic-ai/gpt4all) an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue.\n",
|
||||
"\n",
|
||||
"This example goes over how to use LangChain to interact with `GPT4All` models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Note: you may need to restart the kernel to use updated packages.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%pip install pyllamacpp > /dev/null"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import PromptTemplate, LLMChain\n",
|
||||
"from langchain.llms import GPT4All\n",
|
||||
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"Question: {question}\n",
|
||||
"\n",
|
||||
"Answer: Let's think step by step.\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Specify Model\n",
|
||||
"\n",
|
||||
"To run locally, download a compatible ggml-formatted model. For more info, visit https://github.com/nomic-ai/pyllamacpp\n",
|
||||
"\n",
|
||||
"For full installation instructions go [here](https://gpt4all.io/index.html).\n",
|
||||
"\n",
|
||||
"The GPT4All Chat installer needs to decompress a 3GB LLM model during the installation process!\n",
|
||||
"\n",
|
||||
"Note that new models are uploaded regularly - check the link above for the most recent `.bin` URL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"local_path = './models/gpt4all-lora-quantized-ggml.bin' # replace with your desired local file path"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Uncomment the below block to download a model. You may want to update `url` to a new version."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# import requests\n",
|
||||
"\n",
|
||||
"# from pathlib import Path\n",
|
||||
"# from tqdm import tqdm\n",
|
||||
"\n",
|
||||
"# Path(local_path).parent.mkdir(parents=True, exist_ok=True)\n",
|
||||
"\n",
|
||||
"# # Example model. Check https://github.com/nomic-ai/pyllamacpp for the latest models.\n",
|
||||
"# url = 'https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized-ggml.bin'\n",
|
||||
"\n",
|
||||
"# # send a GET request to the URL to download the file. Stream since it's large\n",
|
||||
"# response = requests.get(url, stream=True)\n",
|
||||
"\n",
|
||||
"# # open the file in binary mode and write the contents of the response to it in chunks\n",
|
||||
"# # This is a large file, so be prepared to wait.\n",
|
||||
"# with open(local_path, 'wb') as f:\n",
|
||||
"# for chunk in tqdm(response.iter_content(chunk_size=8192)):\n",
|
||||
"# if chunk:\n",
|
||||
"# f.write(chunk)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Callbacks support token-wise streaming\n",
|
||||
"callbacks = [StreamingStdOutCallbackHandler()]\n",
|
||||
"# Verbose is required to pass to the callback manager\n",
|
||||
"llm = GPT4All(model=local_path, callbacks=callbacks, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(prompt=prompt, llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
|
||||
"\n",
|
||||
"llm_chain.run(question)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# GPT4All\n",
|
||||
"\n",
|
||||
"[GitHub:nomic-ai/gpt4all](https://github.com/nomic-ai/gpt4all) an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue.\n",
|
||||
"\n",
|
||||
"This example goes over how to use LangChain to interact with `GPT4All` models."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Note: you may need to restart the kernel to use updated packages.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%pip install pygpt4all > /dev/null"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import PromptTemplate, LLMChain\n",
|
||||
"from langchain.llms import GPT4All\n",
|
||||
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"Question: {question}\n",
|
||||
"\n",
|
||||
"Answer: Let's think step by step.\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Specify Model\n",
|
||||
"\n",
|
||||
"To run locally, download a compatible ggml-formatted model. For more info, visit https://github.com/nomic-ai/pygpt4all\n",
|
||||
"\n",
|
||||
"For full installation instructions go [here](https://gpt4all.io/index.html).\n",
|
||||
"\n",
|
||||
"The GPT4All Chat installer needs to decompress a 3GB LLM model during the installation process!\n",
|
||||
"\n",
|
||||
"Note that new models are uploaded regularly - check the link above for the most recent `.bin` URL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"local_path = './models/ggml-gpt4all-l13b-snoozy.bin' # replace with your desired local file path"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Uncomment the below block to download a model. You may want to update `url` to a new version."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# import requests\n",
|
||||
"\n",
|
||||
"# from pathlib import Path\n",
|
||||
"# from tqdm import tqdm\n",
|
||||
"\n",
|
||||
"# Path(local_path).parent.mkdir(parents=True, exist_ok=True)\n",
|
||||
"\n",
|
||||
"# # Example model. Check https://github.com/nomic-ai/pygpt4all for the latest models.\n",
|
||||
"# url = 'http://gpt4all.io/models/ggml-gpt4all-l13b-snoozy.bin'\n",
|
||||
"\n",
|
||||
"# # send a GET request to the URL to download the file. Stream since it's large\n",
|
||||
"# response = requests.get(url, stream=True)\n",
|
||||
"\n",
|
||||
"# # open the file in binary mode and write the contents of the response to it in chunks\n",
|
||||
"# # This is a large file, so be prepared to wait.\n",
|
||||
"# with open(local_path, 'wb') as f:\n",
|
||||
"# for chunk in tqdm(response.iter_content(chunk_size=8192)):\n",
|
||||
"# if chunk:\n",
|
||||
"# f.write(chunk)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Callbacks support token-wise streaming\n",
|
||||
"callbacks = [StreamingStdOutCallbackHandler()]\n",
|
||||
"# Verbose is required to pass to the callback manager\n",
|
||||
"llm = GPT4All(model=local_path, callbacks=callbacks, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(prompt=prompt, llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
|
||||
"\n",
|
||||
"llm_chain.run(question)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
|
||||
@ -12,7 +12,7 @@ from langchain.llms.utils import enforce_stop_tokens
|
||||
class GPT4All(LLM):
|
||||
r"""Wrapper around GPT4All language models.
|
||||
|
||||
To use, you should have the ``pyllamacpp`` python package installed, the
|
||||
To use, you should have the ``pygpt4all`` python package installed, the
|
||||
pre-trained model file, and the model's config information.
|
||||
|
||||
Example:
|
||||
@ -126,19 +126,19 @@ class GPT4All(LLM):
|
||||
def validate_environment(cls, values: Dict) -> Dict:
|
||||
"""Validate that the python package exists in the environment."""
|
||||
try:
|
||||
from pyllamacpp.model import Model as GPT4AllModel
|
||||
from pygpt4all.models.gpt4all import GPT4All as GPT4AllModel
|
||||
|
||||
llama_keys = cls._llama_param_names()
|
||||
model_kwargs = {k: v for k, v in values.items() if k in llama_keys}
|
||||
values["client"] = GPT4AllModel(
|
||||
ggml_model=values["model"],
|
||||
model_path=values["model"],
|
||||
**model_kwargs,
|
||||
)
|
||||
|
||||
except ImportError:
|
||||
raise ValueError(
|
||||
"Could not import pyllamacpp python package. "
|
||||
"Please install it with `pip install pyllamacpp`."
|
||||
"Could not import pygpt4all python package. "
|
||||
"Please install it with `pip install pygpt4all`."
|
||||
)
|
||||
return values
|
||||
|
||||
|
||||
@ -7,21 +7,12 @@ from langchain.llms import GPT4All
|
||||
|
||||
|
||||
def _download_model() -> str:
|
||||
"""Download model.
|
||||
From https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized.bin,
|
||||
convert to new ggml format and return model path."""
|
||||
model_url = "https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized.bin"
|
||||
tokenizer_url = "https://huggingface.co/decapoda-research/llama-7b-hf/resolve/main/tokenizer.model"
|
||||
conversion_script = "https://github.com/nomic-ai/pyllamacpp/blob/main/pyllamacpp/scripts/convert_gpt4all.py"
|
||||
"""Download model."""
|
||||
model_url = "http://gpt4all.io/models/ggml-gpt4all-l13b-snoozy.bin"
|
||||
local_filename = model_url.split("/")[-1]
|
||||
|
||||
if not os.path.exists("convert_gpt4all.py"):
|
||||
urlretrieve(conversion_script, "convert_gpt4all.py")
|
||||
if not os.path.exists("tokenizer.model"):
|
||||
urlretrieve(tokenizer_url, "tokenizer.model")
|
||||
if not os.path.exists(local_filename):
|
||||
urlretrieve(model_url, local_filename)
|
||||
os.system(f"python convert_gpt4all.py.py . tokenizer.model")
|
||||
|
||||
return local_filename
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user