Skip to main content

image image image

🔥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.

Metadata

Release files for llm4chat 2023.4.24.19.22.24

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llm4chat 2023.4.24.19.22.24
File Size Uploaded
llm4chat-2023.4.24.19.22.24.tar.gz 3.8 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for llm4chat 2023.4.24.19.22.24
File Interpreter ABI Platform
llm4chat-2023.4.24.19.22.24-py2.py3-none-any.whl Python 3, Python 2 none any Details

Total release size: 3.8 MB

Release files / llm4chat-2023.4.24.19.22.24.tar.gz

Download URL llm4chat-2023.4.24.19.22.24.tar.gz
Size 3.8 MB
Tags Source
SHA-256 checksum
How to use checksums
40d1964abe85df17a04a38bd6938ca8083e6871ddcf59087b0ad9053307a5f54
BLAKE2b-256 checksum
How to use checksums
e8312227190812c000c940e73ab530d2aabc7f669e7f9ff48116ad63456e9f15
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.8.13

Release files / llm4chat-2023.4.24.19.22.24-py2.py3-none-any.whl

Download URL llm4chat-2023.4.24.19.22.24-py2.py3-none-any.whl
Size 21.2 kB
Tags Python 2 Python 3
SHA-256 checksum
How to use checksums
6a160dcdb1af18b249991d1d629639ae3411ce086fc2e5415a97695be79d8c79
BLAKE2b-256 checksum
How to use checksums
dd860afeb1e0e0f13779727f03a2f9d92761b327080d59cde1c4e2f84bcb7bba
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.8.13
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page