SQL
Batch process all your records to store structured outputs in a PostgreSQL or SQLite schema.
Insert query is currently limited to append.
You will need:
The PostgreSQL or SQLite prerequisites.
For PostgreSQL:
-
A PostgreSQL instance. Install PostgreSQL.
-
The host name and port number for the instance. These values are in the
postgresql.conf
file’slisten_addresses
andport
settings. This file should be on the same machine as the instance. These values might also already be set as environment variables namedPGHOST
andPGPORT
on the same machine as the instance. -
A database in the instance. Create a database.
-
A table in the database. Create a table. See also the Sample index schema.
The table’s schema must match the schema of the documents that Unstructured produces. Unstructured cannot provide a schema that is guaranteed to work in all circumstances. This is because these schemas will vary based on your source files’ types; how you want Unstructured to partition, chunk, and generate embeddings; any custom post-processing code that you run; and other factors.
You can adapt the following table schema example for your own needs:
See also:
- CREATE TABLE for PostgreSQL
- CREATE TABLE for PostrgreSQL with pgvector
- Unstructured document elements and metadata
-
A user in the database, and a password for the user. Create a user.
-
Database access for the user. Give database access to a user.
For SQLite:
-
A SQLite instance. Download and install SQLite.
-
A SQLite database. Create a database.
-
The path to the database’s
.db
file. -
A table in the database. Create a table. See also the Sample index schema.
The table’s schema must match the schema of the documents that Unstructured produces. Unstructured cannot provide a schema that is guaranteed to work in all circumstances. This is because these schemas will vary based on your source files’ types; how you want Unstructured to partition, chunk, and generate embeddings; any custom post-processing code that you run; and other factors.
You can adapt the following table schema example for your own needs:
SQLiteCREATE TABLE elements ( id TEXT PRIMARY KEY, element_id TEXT, text TEXT, embeddings TEXT, parent_id TEXT, page_number INTEGER, is_continuation INTEGER, orig_elements TEXT );
See also:
The PostgreSQL and SQLite connector dependencies:
pip install "unstructured-ingest[postgres]"
You might also need to install additional dependencies, depending on your needs. Learn more.
The following environment variables:
For PostgreSQL:
SQL_DB_TYPE
- The SQL database type. For PostgreSQL, this is alwayspostgresql
, represented by--db-type
(CLI) ordb_type
(Python).PGHOST
- The host name, represented by--host
(CLI) orhost
(Python).PGPORT
- The port number, represented by--port
(CLI) orport
(Python).PGUSER
- The username, represented by--username
(CLI) orusername
(Python).PGPASSWORD
- The user’s password, represented by--password
(CLI) orpassword
(Python).PGDATABASE
- The name of the database, represented by--database
(CLI) ordatabase
(Python).
For SQLite:
SQL_DB_TYPE
- The SQL database type. For SQLite, this is alwayssqlite
, represented by--db-type
(CLI) ordb_type
(Python).SQLITE_DB_PATH
- The path to the database’s.db
file, represented by--database
(CLI) ordatabase
(Python).
Now call the Unstructured Ingest CLI or the Unstructured Ingest Python library. The source connector can be any of the ones supported. This example uses the local source connector:
This example sends files to Unstructured API services for processing by default. To process files locally instead, see the instructions at the end of this page.
For the Unstructured Ingest CLI and the Unstructured Ingest Python library, you can use the --partition-by-api
option (CLI) or partition_by_api
(Python) parameter to specify where files are processed:
-
To do local file processing, omit
--partition-by-api
(CLI) orpartition_by_api
(Python), or explicitly specifypartition_by_api=False
(Python).Local file processing does not use an Unstructured API key or API URL, so you can also omit the following, if they appear:
--api-key $UNSTRUCTURED_API_KEY
(CLI) orapi_key=os.getenv("UNSTRUCTURED_API_KEY")
(Python)--partition-endpoint $UNSTRUCTURED_API_URL
(CLI) orpartition_endpoint=os.getenv("UNSTRUCTURED_API_URL")
(Python)- The environment variables
UNSTRUCTURED_API_KEY
andUNSTRUCTURED_API_URL
-
To send files to Unstructured API services for processing, specify
--partition-by-api
(CLI) orpartition_by_api=True
(Python).Unstructured API services also requires an Unstructured API key and API URL, by adding the following:
--api-key $UNSTRUCTURED_API_KEY
(CLI) orapi_key=os.getenv("UNSTRUCTURED_API_KEY")
(Python)--partition-endpoint $UNSTRUCTURED_API_URL
(CLI) orpartition_endpoint=os.getenv("UNSTRUCTURED_API_URL")
(Python)- The environment variables
UNSTRUCTURED_API_KEY
andUNSTRUCTURED_API_URL
, representing your API key and API URL, respectively.
Was this page helpful?