2 使用大模型 做路由层
{"方向1":{'小方向1':'', '小方向2':"", "如何解决河道问题":"",} "方向2":}
方法 类似github 分支 分支与合并的关系 1 - 2 - 3 - 4 \ 2-1 \ 3-1 \ 2-2/ \ 3-2
使用树的数据结构, 并进行串联
概念
什么是河道: 河道: 1 2 3 4 5 11 22 33 44 55
client
1 抽取出这些文件
2 经过路由层
路由层 ---->
queryer
3 对于经过路由层处理归类好的文章进行合并
4 对初始化的文章结构采用合并的策略
5 对于添加动作, 则是维持之前的决策结构不大变化, 而微调其结构
6 是否验证的标签, 这很重要 未来还可以加入概率或者神经网络方式
7 调用 TODO 然后再说
from article_forestz import MyLocalLLMClient,MyArticleDecisionMaker,ArticleForest
For local testing, using a simpler model or mock:
my_llm_client = MyLocalLLMClient(
model_name="gemini-2.5-flash-preview-04-17-nothinking"
)
my_decision_maker = MyArticleDecisionMaker(llm_client=my_llm_client)
article_forest = ArticleForest(article_decision_maker=my_decision_maker)
inputs = [{"id": "Init1", "content": text1}, {"id": "Init2", "content": text2}, {"id": "Init3", "content": text3}]
article_forest.build_initial_forest(inputs)
article_forest.print_tree() article_forest.export_graphviz()
new_articles = [ {"id": "NewA1", "content": test4}, # 归入AI类,可能作为新子层 ]
for article in new_articles: article_forest.add_article(article["content"], article["id"])
Metadata
Release files for article-forestz 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| article_forestz-0.1.2.tar.gz | 11.7 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| article_forestz-0.1.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 23.9 kB
Release files / article_forestz-0.1.2.tar.gz
| Download URL | article_forestz-0.1.2.tar.gz |
|---|---|
| Size | 11.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8241da4b27296722e0756f30b5fbc10cf9192a340199794713be11ae254d666c
|
|
BLAKE2b-256 checksum How to use checksums |
a6aeba698c8517e62f9bd66b6f06467fb2a60796194a418008f6e623ebac7608
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.11
|
Release files / article_forestz-0.1.2-py3-none-any.whl
| Download URL | article_forestz-0.1.2-py3-none-any.whl |
|---|---|
| Size | 12.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
da0605195f6fb9e4992fdfecdc0f8ad86ac323f3864791c1cf43ff0731a569d9
|
|
BLAKE2b-256 checksum How to use checksums |
1e63edbdf85a8a6389a1f5842d4f142aca3599227ff69dd2b5f7e8b15e207fad
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.6.11
|
Security for article-forestz 0.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.