Create a Python package.
Project description
🔥LLM4GPT 为大模型而生🔥
Install
pip install -U llm4gpt
Docs
Usages
from llm.qa import QA
from llm.kb import FaissANN
from llm.chatllm import ChatLLM
from llm.utils import llm_load
from meutils.pipe import *
# 解析知识库
texts = []
metadatas = []
for p in Path('data').glob('*.txt'):
texts.append(p.read_text())
metadatas.append({'source': p})
# 文档向量化
faissann = FaissANN(model_name_or_path="shibing624/text2vec-base-chinese")
faissann.add_texts(texts, metadatas)
# 构建pipeline
model, tokenizer = llm_load(model_name_or_path="THUDM/chatglm-6b", device='cpu')
glm = ChatLLM()
glm.chat_func = partial(model.chat, tokenizer=tokenizer)
qa = QA(glm, faiss_ann=faissann.faiss_ann)
qa.get_knowledge_based_answer('周杰伦在干吗')
qa.get_knowledge_based_answer('姚明住哪里')
TODO
-
增加UI
-
增加本地知识库组件
-
增加互联网搜索组件
-
增加知识图谱组件
-
增加微调模块
-
增加流式输出
======= History
0.0.0 (2023-04-11)
- First release on PyPI.
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
Built Distribution
Close
Hashes for llm4gpt-2023.4.21.14.8.20.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 014eec39282b7e8eb541dad05fb29582242c58d74eeaef8c7e696f88c3aafc69 |
|
MD5 | 27e8a628ac1a7e17f2f51811f4e00670 |
|
BLAKE2b-256 | ff39c10442c6fb73a6f0c724babe82d0571e614ad175e04492341af0a9c12b5a |
Close
Hashes for llm4gpt-2023.4.21.14.8.20-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | fed18011c9858c95fd402bbb6c1d646d3208bcaf4eb17d17eeea3b44c46a96ba |
|
MD5 | 55483785d7fc68922f1dc617b639818a |
|
BLAKE2b-256 | bd87714aa86a5f0f02e0bc4027c1c8d4267f784274eda8d778b62269a9e7ba24 |