Spaces:
Sleeping
Sleeping
Create rag_config.py
Browse files- rag_config.py +29 -0
rag_config.py
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from pathlib import Path
|
| 2 |
+
import json
|
| 3 |
+
|
| 4 |
+
ROOT_DIR = Path(__file__).resolve().parent
|
| 5 |
+
DATA_DIR = ROOT_DIR / "data"
|
| 6 |
+
|
| 7 |
+
CHUNKS_PATH = DATA_DIR / "chunks.jsonl"
|
| 8 |
+
THREADS_PATH = DATA_DIR / "threads.json"
|
| 9 |
+
MESSAGES_PATH = DATA_DIR / "messages.json"
|
| 10 |
+
EMBEDDINGS_PATH = DATA_DIR / "embeddings.npy"
|
| 11 |
+
CHUNK_IDS_PATH = DATA_DIR / "chunk_ids.json"
|
| 12 |
+
|
| 13 |
+
RUNS_DIR = ROOT_DIR / "runs"
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
def load_json(path: Path):
|
| 17 |
+
with path.open("r", encoding="utf-8") as f:
|
| 18 |
+
return json.load(f)
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
def load_jsonl(path: Path):
|
| 22 |
+
items = []
|
| 23 |
+
with path.open("r", encoding="utf-8") as f:
|
| 24 |
+
for line in f:
|
| 25 |
+
line = line.strip()
|
| 26 |
+
if not line:
|
| 27 |
+
continue
|
| 28 |
+
items.append(json.loads(line))
|
| 29 |
+
return items
|