Skip to content

Commit aaa7592

Browse files
committed
Update readme
1 parent 74d28ba commit aaa7592

File tree

1 file changed

+8
-3
lines changed

1 file changed

+8
-3
lines changed

text_2_sql/data_dictionary/README.md

Lines changed: 8 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -52,8 +52,13 @@ A full data dictionary must be built for all the views / tables you which to exp
5252

5353
Manually creating the `entities.json` is a time consuming exercise. To speed up generation, a mixture of SQL Queries and an LLM can be used to generate a initial version. Existing comments and descriptions in the database, can be combined with sample values to generate the necessary descriptions. Manual input can then be used to tweak it for the use case and any improvements.
5454

55-
`data_dictionary_creator.py` contains a utility class that handles the automatic generation and selection of schemas from the source SQL database. It must be subclassed to the appropriate engine.
56-
57-
`sql_server_data_dictionary_creator.py` contains a subclassed version of `data_dictionary_creator.py` that implements the SQL Server specific functionality to extract the entities.
55+
`data_dictionary_creator.py` contains a utility class that handles the automatic generation and selection of schemas from the source SQL database. It must be subclassed to the appropriate engine to handle engine specific queries and connection details.
5856

5957
See `./generated_samples/` for an example output of the script. This can then be automatically indexed with the provided indexer for the **Vector-Based Approach**.
58+
59+
The following Databases have pre-built scripts for them:
60+
61+
- **Microsoft SQL Server:** `sql_server_data_dictionary_creator.py`
62+
- **Snowflake:** `snowflake_data_dictionary_creator.py`
63+
64+
If there is no pre-built script for your database engine, take one of the above as a starting point and adjust it.

0 commit comments

Comments
 (0)