This commit is contained in:
Jonas Braus
2024-12-12 13:44:08 +01:00
+25 -1
View File
@@ -1,7 +1,8 @@
import ollama import ollama
import pymupdf import pymupdf
import os import os
from minio import Minio
from minio.error import S3Error
import chunker import chunker
import lib import lib
import json import json
@@ -16,6 +17,15 @@ from tqdm import tqdm
count = 0 count = 0
def retrieve_file_contents(path): def retrieve_file_contents(path):
#Minio Connection
minioClient = Minio(
"localhost:9000",
access_key="PVFOeJbx87rQyi0WXF1X",
secret_key="Am8Cd9auYGbEGuEXfJtnWEPsMwJCx9N58NCNHCgs",
secure=False,
)
file_extraction_functions = { file_extraction_functions = {
"pdf": lambda path: lib.extract_text_and_pictures(path), "pdf": lambda path: lib.extract_text_and_pictures(path),
"jpg": lambda path: lib.extract_image_content(path), "jpg": lambda path: lib.extract_image_content(path),
@@ -31,6 +41,20 @@ def retrieve_file_contents(path):
print("Parsing files...") print("Parsing files...")
for file in tqdm(files): for file in tqdm(files):
content = file_extraction_functions[file[0]](file[1]) content = file_extraction_functions[file[0]](file[1])
with open(f"./{file[2]}.txt", "w") as future_s3_file:
future_s3_file.writelines(file[1] + "\n" + content)
future_s3_file.flush()
future_s3_file.close()
minioClient.fput_object(
bucket_name="datafiles",
object_name=f"{file[2]}.txt",
file_path=file[1],
)
os.remove(f"./{file[2]}.txt")
contents.append({ contents.append({
"type": file[0], "type": file[0],
"path": file[1], "path": file[1],