Skip to main content

Create a Python package.

Project description

image image image

🔥ChatLLM🔥


Install

pip install -U llm4gpt

Docs

Usages

from chatllm.utils import load_llm4chat
from chatllm.applications import ChatBase

chat_func = load_llm4chat("THUDM/chatglm-6b")

qa = ChatBase(chat_func=chat_func)

for i, _ in qa(query='周杰伦是谁', knowledge_base='周杰伦是傻子'):
    print(_, flush=True)


# 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-2023.4.26.9.16.17.tar.gz (6.1 MB view details)

Uploaded Source

Built Distribution

ChatLLM-2023.4.26.9.16.17-py3-none-any.whl (24.4 kB view details)

Uploaded Python 3

File details

Details for the file ChatLLM-2023.4.26.9.16.17.tar.gz.

File metadata

  • Download URL: ChatLLM-2023.4.26.9.16.17.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-2023.4.26.9.16.17.tar.gz
Algorithm Hash digest
SHA256 e22025861911c0948edcaf6a85e97f1df1d16dd0f82533221b1ce819d12ccdca
MD5 c1a34c65373d4a1fe66ff7a134a4ceb2
BLAKE2b-256 ad40a696d1ebe7a9e9b5ab21776394002c65a7af8bd8f803b17bf8f1a3112062

See more details on using hashes here.

File details

Details for the file ChatLLM-2023.4.26.9.16.17-py3-none-any.whl.

File metadata

File hashes

Hashes for ChatLLM-2023.4.26.9.16.17-py3-none-any.whl
Algorithm Hash digest
SHA256 f11783f1b60506cff2a071287dff44bd03d4899eaeecf870c29ee151083aee02
MD5 13aa91e2605dedc410239e68f462ebbb
BLAKE2b-256 3142ea7e1653a82e925f903fec3e984daf4d2bdca6282a718cb22d815c2eb730

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