[Summary] HugeGraph-ai roadmap & Contribution Wanted #2
Comments
|
I would like to implement the feature Knowledge graph construction by llm， thank you！ |
imbajin
changed the title
|
I want to try python code review & test . |
Hi @frankjiang777 , can u try to implement #14 ? if you need help, just contact me. |
|
hi, @simon824 ,I want to try extract schema from HugeGraph for kg construction! |
Hi @haohao0103 , is it still in progress? |
|
Hi, @simon824 is the task "Introduce FastAPI as the web framework of hugegraph-ai" still available and can I work on it? |
simon824
pushed a commit
that referenced
this issue
Jul 23, 2024
…n. (#54) * 1. 修改配置方式，整体配置简单易用。 2. Graph RAG增加向量索引和混合索引加重排的两种方式的索引。 3. 增加自然语言转gremlin的任务及演示。 * reafact: add conn check after applying configs (WIP) TODO: lack some check now * fix: use log to print some info * feat(llm): support qianfan platform for embedding & replace wenxin refer * 1. 修复了导入和搜索的bug * fix upload document * fix the non-disambiguate uploading * chore: exclude binary files & update params order * fix: openai params not match * log: record error in py-client with orange color for debug RESTful API problem * 1. added triples and edges id setting 2. added template input textbox 3. changed ernie llm to use qianfan sdk 4. added function of filtering id length * refact: update the prompt template Also rename the same params (inner & outer) TODO: Non-Schema mode will throw Error now (we need fix it) * update: add config file argument and update to build semantic vertex-id querying - Update BuildSemanticIndex class to match new file naming convention. - Modify code_format_and_analysis.sh to use a line length of 120. - Change logging format to use %s instead of {} for string formatting. * feat: optimize index loading and add clean-up button 1. Introduce a clean-up function to remove index and content files, aiding in maintaining a clean file system after operations. 2. Introduce default demo of build kg. 3. Now it does not clean the kg before building kg by default. 4. Clean the stopwords files. * Add generating operation of config file in README.md * fix: use lower case to compare str & enhance the extract prompt * fix: Fix to add triples from extracted vertex, and fix the format of triples. * doc: update readme * feat: use custom_handler log color * fix: avoid FSRF security warning * doc: update readme * feat: change config store method * chore: use a flexible version for dependencies * feat(hugegraph_llm): supporting property graph extract and primary key id. (#2) * fix: token type should be int (WIP) init graphspace support * fix: read int parameter from .env * feat: use .env as default config file * fix: Add a 'copy' button to the output box * Support local openai env (#1) * support local openai env * fix env * refact: set gpt-4o-mini as the openai default type * feat: Add rag option for four output type including "llm-raw", "graph-only", "vector-only", "graph-vector" * feat: Add vector result output in cmd. * feat: Add error catch and display it on the front-end web interface, fix code style (#3) * fix: fix the triple extract * 修改格式，和属性图模式 * 修复代码样式，并增加错误抓取和传输到前端界面 * revert: graphspace init for CI --------- Co-authored-by: imbajin <jin@apache.org> Co-authored-by: chenzihong <522023320011@smail.nju.edu.cn> Co-authored-by: Liu Jiajun <85552719+jasinliu@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Feature Description (功能描述)
If you are interested in the following tasks, feel free to claim them. Just comment below with the feature you would like to implement and create the corresponding issue.
Welcome everyone to provide relevant suggestions and participate in this plan~ 💯
Reference:
The text was updated successfully, but these errors were encountered: