puuuuush

lib.py

@@ -1,7 +1,9 @@
 import os, pymupdf, whisper, json
 
 import cv2
+import psycopg2
 import pytesseract
+import ollama
 
 
 def read_files(path, output, filetypes=None):
@@ -40,3 +42,20 @@ def extract_image_content(path):
     pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
     img = cv2.imread(path)
     return pytesseract.image_to_string(img)
+
+def prompt_embedding(prompt):
+    embedding = ollama.embeddings(model="mxbai-embed-large", prompt=prompt)
+
+    conn = psycopg2.connect(
+        dbname="embeddings",
+        user="python",
+        password="PasswordPassword123",
+        host="localhost",
+        port="5555"
+    )
+    cur = conn.cursor()
+
+    cur.execute(f"select id, filepath, embedding, embedding <-> {embedding} as distance from dbtable order by distance limit 1;")
+
+    result = cur.fetchall()
+    print(result)