puuuuush

Puuuuush it babyyyyy
DEEEEEEPER

main.py

@@ -1,7 +1,11 @@
+import ollama
 import pymupdf
 import os
 import lib
 import json
+import psycopg2
+
+
 
 def retrieve_file_contents(path):
     file_extraction_functions = {
@@ -30,5 +34,50 @@ def retrieve_file_contents(path):
 contents = retrieve_file_contents("C:\\Users\\afist\\Downloads\\SoftwareEng")
 
 
+embedding_list = []
 
-print(json.dumps(contents, indent="\t"))
+def create_embeddings(pContent):
+    conn = psycopg2.connect(
+        dbname="embeddings",
+        user="python",
+        password="PasswordPassword123",
+        host="localhost",
+        port="5555"
+    )
+    cur = conn.cursor()
+
+    create_table_query = '''
+        create table if not exists dbtable (
+        id SERIAL PRIMARY KEY,
+        filename TEXT NOT NULL,
+        embedding  VECTOR NOT NULL
+        )
+    '''
+
+
+    cur.execute(create_table_query)
+
+    cur.execute('CREATE EXTENSION IF NOT EXISTS vector;')
+    for content in pContent:
+        merged_info = "Dateiname: " + content["filename"] + " Dateiinhalt: " + content[
+            "content"]  # Bessere Embeddings mit Dateiname // Information vorne dran?
+        # print(merged_info)
+        response = ollama.embeddings(model="mxbai-embed-large", prompt=merged_info)
+        #embedding_list.append(response["embedding"])
+        insert_data = f'insert into dbtable (filepath, embedding) Values ({content["filepath"]}, {response["embedding"]});'
+        cur.execute(insert_data)
+
+    conn.commit()
+    conn.close()
+
+
+
+
+
+
+
+
+create_embeddings(contents)
+
+
+#print(json.dumps(contents, indent="\t"))