Skip to main content

Add your description here

Project description

Welcome to QueryPipZ

应该如何使用该仓库

1 合理的维护所有的factory 工厂 例如 docstore, vectorstore, graphstore

2 构建并存续特异化的builderlib

3 注册到director 中的 buildtype中

1 初始化 build

在第一次使用的时候,需要初始化, 如果定义了reader 则text 是否传入均可 如果没有定义reader 则 比如传入text

from querypipz import BuilderFactory,BuilderType,Director

dirs = Director(BuilderFactory(BuilderType.CHAT_HISTORY_MEMORY_BUILDER))

query = dirs.construct()



text = """
user: hello
assistant: Hello! How can I assist you today?
user: 你在说什么?
assistant: 你好!我可以帮你做些什么呢?
user: 考虑一下
assistant: 你能具体说明一下需要我考虑什么吗?
user: 考虑一下做一个皮卡丘
assistant: 你是想让我考虑做一个皮卡丘的什么呢?是画一个皮卡丘,还是制作一个皮卡丘模型,或者其他什么呢?请告诉我更多细节。
user: 让我想想
"""

query.build(text = text,cover= True)

2 初始化构建过以后, 直接update上传

from querypipz import BuilderFactory,BuilderType,Director

dirs = Director(BuilderFactory(BuilderType.CHAT_HISTORY_MEMORY_BUILDER))

query = dirs.construct()



text = """
user: 再一次hello
assistant: Hello! How can I assist you today?
user: 你在说什么?
assistant: 你好!我可以帮你做些什么呢?
user: 考虑一下
assistant: 你能具体说明一下需要我考虑什么吗?
user: 考虑一下做一个皮卡丘
assistant: 你是想让我考虑做一个皮卡丘的什么呢?是画一个皮卡丘,还是制作一个皮卡丘模型,或者其他什么呢?请告诉我更多细节。
user: 让我想想
"""

query.update(prompt = text)

直接调取retriver 和query 不需要初始化

retriver

query.retrieve_search('hello')

query

query.query('hello')

tools

query.tools('kv.html')

querypipz

我们的任务就是要构建一个在query 之前, 甚至在chat 之前的所有动作的包

应该如何使用该仓库

1 合理的维护所有的factory 工厂 例如 docstore, vectorstore, graphstore

2 构建并存续特异化的builderlib

3 注册到director 中的 buildtype中

""" VectorStore from document from vectorstore 内有数据 √(创建时会存储) √(及时存储) 内无数据 √ √(需要以创建) """

0-1 query pipeline 1 多模态 2

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llamahelper-0.1.5.tar.gz (29.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llamahelper-0.1.5-py3-none-any.whl (38.2 kB view details)

Uploaded Python 3

File details

Details for the file llamahelper-0.1.5.tar.gz.

File metadata

  • Download URL: llamahelper-0.1.5.tar.gz
  • Upload date:
  • Size: 29.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.11

File hashes

Hashes for llamahelper-0.1.5.tar.gz
Algorithm Hash digest
SHA256 421a2a92a7fff054722f580d01d4471db5406987b833bcc708f80c6937800b64
MD5 8a4677d091ef57572d706626a7a906c1
BLAKE2b-256 5a80e1398d05289dafc9d37e6d5645309b7d37830c734b4f7d196be85d7d2f79

See more details on using hashes here.

File details

Details for the file llamahelper-0.1.5-py3-none-any.whl.

File metadata

File hashes

Hashes for llamahelper-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 cbf50b986b5d7f43bfcd09c8e38ea6949720f4de968df5978419f8eeda1ffb75
MD5 9316c0d0469db0d665deb2bc86a055ac
BLAKE2b-256 acfcfa540134e0082cb34f69d18b43953804e491ba5a074b7cdcb4a86063f18a

See more details on using hashes here.

Supported by

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