Skip to main content

Create a Python package.

Project description

image image image

🔥ChatLLM🔥


Install

pip install -U llm4gpt

Docs

Usages

from chatllm.his._qa import QA
from chatllm.his import FaissANN
from chatllm.his._chatllm import ChatLLM
from chatllm.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

ChatLLM-2023.4.25.16.33.8.tar.gz (6.1 MB view details)

Uploaded Source

Built Distribution

ChatLLM-2023.4.25.16.33.8-py3-none-any.whl (22.4 kB view details)

Uploaded Python 3

File details

Details for the file ChatLLM-2023.4.25.16.33.8.tar.gz.

File metadata

  • Download URL: ChatLLM-2023.4.25.16.33.8.tar.gz
  • Upload date:
  • Size: 6.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.13

File hashes

Hashes for ChatLLM-2023.4.25.16.33.8.tar.gz
Algorithm Hash digest
SHA256 4efb54c7af23d10ba52ef9c5203401ea44bd1f81f19f6e96048194052cdacdd7
MD5 24947b2708a1cf5bbbb8923d94cb7ad4
BLAKE2b-256 c83c290bedd5a3bd3ae40f275dfb540a02c8f196db19204779f74ac0d511a72b

See more details on using hashes here.

File details

Details for the file ChatLLM-2023.4.25.16.33.8-py3-none-any.whl.

File metadata

File hashes

Hashes for ChatLLM-2023.4.25.16.33.8-py3-none-any.whl
Algorithm Hash digest
SHA256 1cf21c4a2a5ebd798a9e53ef840d5d963987f266471b319eae8b1faf58896a04
MD5 18246c191b2b591619c003ecd977316e
BLAKE2b-256 1911f40812a050f6bd3a1723e7a0124fb875d0a4d1af1e9fa3f39d60a6470709

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page