Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

update readmes #9

Merged
merged 1 commit into from
Nov 15, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion Model/README.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,10 @@
# 進行檢索的主程式
# 執行檢索的主程式

# 使用技術
- Hybrid Search (Stage 1 --> Get Top 100)
- OpenAI Embedding Model (Semantic search): `text-embedding-3-large` (50% Search)
- Bm25 (Keyword search): `weaviate gse (jieba)` (50% Search)
- Voyage Reranker (Stage 2 --> Get Top 1)

## flask_app.py
- `/` 是 API Docs, `/api/chat/` 是我們的 Retrieval API
Expand Down
6 changes: 4 additions & 2 deletions Preprocess/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,9 @@
包含 資料預處理 及 資料寫入資料庫

## data_process/
OCR & PDF 文字直接讀取
使用 Tesseract OCR & PDF Plumber/Miner 將 PDF 轉換為文字

## insert_data.py
此程式為寫入資料庫的程式碼,並包含建立資料庫 class、對資料進行 embedding、利用 text_splitter 去 chunk tokens 數過多的資料
- 此程式為寫入資料庫的程式碼,並包含建立資料庫 class、對資料進行 embedding
- 利用 text_splitter 來 chunk tokens 數過多的資料
- 2000 tokens 一切、500 tokens 重疊
15 changes: 15 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,20 @@
# AI CUP 2024 玉山人工智慧公開挑戰賽-RAG與LLM在金融問答的應用

## 使用技術

### Retriever

- Hybrid Search (Stage 1 --> Get Top 100)
- OpenAI Embedding Model (Semantic search): `text-embedding-3-large` (50% Search)
- Bm25 (Keyword search): `weaviate gse (jieba)` (50% Search)
- Voyage Reranker (Stage 2 --> Get Top 1)

### Data Preprocess

- 使用 Tesseract OCR & PDF Plumber/Miner 將 PDF 轉換為文字
- 利用 text_splitter 來 chunk tokens 數過多的資料
- 2000 tokens 一切、500 tokens 重疊

## Repo Structure
```
.
Expand Down
Loading