Oracle AI Database - Document Processing

import sys

import oracledb

# Please update with your username, password, hostname, port and service_name
username = "<username>"
password = "<password>"
dsn = "<hostname>:<port>/<service_name>"

connection = oracledb.connect(user=username, password=password, dsn=dsn)
print("Connection successful!")

try:
    cursor = conn.cursor()

    drop_table_sql = """drop table if exists demo_tab"""
    cursor.execute(drop_table_sql)

    create_table_sql = """create table demo_tab (id number, data clob)"""
    cursor.execute(create_table_sql)

    insert_row_sql = """insert into demo_tab values (:1, :2)"""
    rows_to_insert = [
        (
            1,
            "If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.",
        ),
        (
            2,
            "A tablespace can be online (accessible) or offline (not accessible) whenever the database is open.\nA tablespace is usually online so that its data is available to users. The SYSTEM tablespace and temporary tablespaces cannot be taken offline.",
        ),
        (
            3,
            "The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table.\nSometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.",
        ),
    ]
    cursor.executemany(insert_row_sql, rows_to_insert)

    conn.commit()

    print("Table created and populated.")
    cursor.close()
except Exception as e:
    print("Table creation failed.")
    cursor.close()
    conn.close()
    sys.exit(1)

from langchain_oracledb.document_loaders.oracleai import OracleDocLoader
from langchain_core.documents import Document

"""
# loading a local file
loader_params = {}
loader_params["file"] = "<file>"

# loading from a local directory
loader_params = {}
loader_params["dir"] = "<directory>"
"""

# loading from Oracle Database table
loader_params = {
    "owner": "<owner>",
    "tablename": "demo_tab",
    "colname": "data",
}

""" load the docs """
loader = OracleDocLoader(conn=conn, params=loader_params)
docs = loader.load()

""" verify """
print(f"Number of docs loaded: {len(docs)}")
# print(f"Document-0: {docs[0].page_content}") # content

from langchain_oracledb.document_loaders.oracleai import OracleTextSplitter
from langchain_core.documents import Document

"""
# Some examples
# split by chars, max 500 chars
splitter_params = {"split": "chars", "max": 500, "normalize": "all"}

# split by words, max 100 words
splitter_params = {"split": "words", "max": 100, "normalize": "all"}

# split by sentence, max 20 sentences
splitter_params = {"split": "sentence", "max": 20, "normalize": "all"}
"""

# split by default parameters
splitter_params = {"normalize": "all"}

# get the splitter instance
splitter = OracleTextSplitter(conn=conn, params=splitter_params)

list_chunks = []
for doc in docs:
    chunks = splitter.split_text(doc.page_content)
    list_chunks.extend(chunks)

""" verify """
print(f"Number of Chunks: {len(list_chunks)}")
# print(f"Chunk-0: {list_chunks[0]}") # content