/var/opt/nydus/ops/mysql/ai/genai/__pycache__
Edit: /var/opt/nydus/ops/mysql/ai/genai/__pycache__/embedding.cpython-312.pyc (7666B)
N j d Z ddlmZmZmZ ddlZddlmZ ddl m
Z
ddl m Z m
Z
mZmZmZmZmZ ddlmZ G d d e Zy)
zEmbeddings integration utilities for MySQL Connector/Python.
Provides MyEmbeddings class to generate embeddings via MySQL HeatWave
using ML_EMBED_TABLE and ML_EMBED_ROW.
)DictListOptionalN)
Embeddings) PrivateAttr)atomic_transaction execute_sqlformat_value_sql
source_schemasql_table_from_dfsql_table_to_dftemporary_sql_tables)MySQLConnectionAbstractc e Zd ZU dZ e Zeed< d dedee f fd
Z
de e de e e
fdZd e de e
fd
Z xZS ) MyEmbeddingsa
Embedding generator class that uses a MySQL database to compute embeddings for input text.
This class batches input text into temporary SQL tables, invokes MySQL's ML_EMBED_TABLE
to generate embeddings, and retrieves the results as lists of floats.
Attributes:
_db_connection (MySQLConnectionAbstract): MySQL connection used for all database operations.
schema_name (str): Name of the database schema to use.
options_placeholder (str): SQL-ready placeholder string for ML_EMBED_TABLE options.
options_params (dict): Dictionary of concrete option values to be passed as SQL parameters.
_db_connection
db_connectionoptionsc t | || _ t | | _ |xs i }t | \ | _ | _ y)a
Initialize MyEmbeddings with a database connection and optional embedding parameters.
References:
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-embed-row.html
A full list of supported options can be found under "options"
NOTE: The supported "options" are the intersection of the options provided in
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-embed-row.html
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-embed-table.html
Args:
db_connection: Active MySQL connector database connection.
options: Optional dictionary of options for embedding operations.
Raises:
ValueError: If the schema name is not valid
DatabaseError:
If a database connection issue occurs.
If an operational error occurs during execution.
N)super__init__r r schema_namer
options_placeholderoptions_params)selfr r __class__s I/opt/nydus/tmp/pip-target-a90h98xg/lib/python/mysql/ai/genai/embedding.pyr zMyEmbeddings.__init__F sC 0 +( 7-R8H8Q5 $"5 textsreturnc |sg S t j t t | |d }t | j
5 }t
| j
5 }t || j | \ }}|j | j |f d| d| d| j d}t ||| j t || j | }|d j j st d |d D r t! d |d j# } | D
cg c]
}
t% |
} }
| cd
d
d
cd
d
d
S c c}
w # 1 sw Y nxY w d
d
d
y
# 1 sw Y y
xY w) a
Generate embeddings for a list of input texts using the MySQL ML embedding procedure.
References:
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-embed-table.html
Args:
texts: List of input strings to embed.
Returns:
List of lists of floats, with each inner list containing the embedding for a text.
Raises:
DatabaseError:
If provided options are invalid or unsupported.
If a database connection issue occurs.
If an operational error occurs during execution.
ValueError:
If one or more text entries were unable to be embedded.
Implementation notes:
- Creates a temporary table to pass input text to the MySQL embedding service.
- Adds a primary key to ensure results preserve input order.
- Calls ML_EMBED_TABLE and fetches the resulting embeddings.
- Deletes the temporary table after use to avoid polluting the database.
- Embedding vectors are extracted from the "embeddings" column of the result table.
)idtextzCALL sys.ML_EMBED_TABLE('z .text', 'z.embeddings', )params
embeddingsc 3 $ K | ] }|d u
y wN ).0es r
z/MyEmbeddings.embed_documents.. s A#>aT #>s z:Failure to generate embeddings for one or more text entry.N)pd DataFramerangelenr r r r r appendr r r r
isnullany
ValueErrortolistlist) r r dfcursortemporary_tablesqualified_table_name
table_name embed_query
df_embeddingsr' r, s r embed_documentsz MyEmbeddings.embed_documentsd s 8 I
\\s5z!2EB
C
t 2 2 3v !4!4 59I/@(("0 , *
# #T%5%5z$B C() *() ++,
D4G4G H ,FD4D4Dj QM \*113779S A#0 #>A > !P
'|4;;=J+56:a$q':J6 ?
6 5
4 3< 7;
6 5 5
4 3 3s7 E2CE /EE E2E E% !E22E;r# c t | j 5 }t |d| j d|g| j t |j
d cddd S # 1 sw Y yxY w)a
Generate an embedding for a single text string.
References:
https://dev.mysql.com/doc/heatwave/en/mys-hwgenai-ml-embed-row.html
Args:
text: The input string to embed.
Returns:
List of floats representing the embedding vector.
Raises:
DatabaseError:
If provided options are invalid or unsupported.
If a database connection issue occurs.
If an operational error occurs during execution.
Example:
>>> MyEmbeddings(db_conn).embed_query("Hello world")
[0.1, 0.2, ...]
z SELECT sys.ML_EMBED_ROW("%s", r$ r% r N)r r r r r r7 fetchone)r r# r9 s r r= zMyEmbeddings.embed_query se . 3 3
4 01I1I0J!L 3t 2 23
)!,-
5
4
4s AA&&A/r) )__name__
__module__ __qualname____doc__r r r __annotations__r r r r strfloatr? r=
__classcell__)r s @r r r 6 su /:mN+; QU R 4 R?G~ RrP s= : ( ' 0 >O.: O.r