ryan/simbarag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adding some funny stuff #2

Merged
ryan merged 3 commits from data-preprocessing into main 2025-07-30 20:30:34 -04:00
Conversation 0 Commits 3 Files Changed 5 +4 -3
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit c7152d3f32 - Show all commits

7
main.py
View File

@@ -1,4 +1,5 @@
import logging import logging
import os
import argparse import argparse
import chromadb import chromadb
@@ -11,7 +12,9 @@ from chunker import Chunker
from dotenv import load_dotenv from dotenv import load_dotenv
client = chromadb.PersistentClient(path="/Users/ryanchen/Programs/raggr/chromadb") load_dotenv()
client = chromadb.PersistentClient(path=os.getenv("CHROMADB_PATH", ""))
simba_docs = client.get_or_create_collection(name="simba_docs") simba_docs = client.get_or_create_collection(name="simba_docs")
feline_vet_lookup = client.get_or_create_collection(name="feline_vet_lookup") feline_vet_lookup = client.get_or_create_collection(name="feline_vet_lookup")
@@ -24,8 +27,6 @@ parser.add_argument(
"--reindex", action="store_true", help="re-index the simba documents" "--reindex", action="store_true", help="re-index the simba documents"
) )
load_dotenv()
def chunk_data(texts: list[str], collection): def chunk_data(texts: list[str], collection):
# Step 2: Create chunks # Step 2: Create chunks