Icici

pipelines.extraction.llama.banks.icici

Summary

Icici bank-specific port implementations (llama objects path).

The llama objects are already normalized per-transaction (date / amount / balance / description / direction), so there is no bank-specific column logic. IciciLlamaObjectsReaderPort mirrors the icici OG bank CONFIG {"limit_first": True} (keeps only the primary account bucket), matching the 223-txn llama run stored in the DB. IciciLlamaExtractionPipeline pins the reader; the shared objects policy (stated balances trusted) is identical across banks.

Classes

IciciLlamaExtractionPipeline

Bases: ImplLlamaExtractionPipeline

Icici llama graph root — pins the Icici objects reader.

Attributes:

Name	Type	Description
`objects_reader`	`IciciLlamaObjectsReaderPort`	Icici objects reader.

Functions

run

run(source) -> List[Any]

Run the llama objects extraction chain.

Parameters:

Name	Type	Description	Default
`source`		Raw extraction source.	required

Returns:

Type	Description
`List[Any]`	List[Any]: Raw expense records.

IciciLlamaObjectsReaderPort

Bases: ImplLlamaObjectsReaderPort

Icici llama objects reader — primary bucket only (OG icici CONFIG).

Attributes:

Name	Type	Description
`limit_first`	`bool`	Whether to keep only the primary bucket.

Functions

filter_objects

filter_objects(
    objects: List[Any], *, limit_first: bool = False
) -> List[dict]

Filter objects to rows between balance-forward marker rows.

Parameters:

Name	Type	Description	Default
`objects`	`List[Any]`	Structured statement objects.	required
`limit_first`	`bool`	Keep only the first bucket. Defaults to False.	`False`

Returns:

Type	Description
`List[dict]`	List[dict]: Records between (and after) marker rows.

read

read(objects) -> List[dict]

Read structured objects, applying the row-level bucket filter.

Parameters:

Name	Type	Description	Default
`objects`		List of structured statement objects.	required

Returns:

Type	Description
`List[dict]`	List[dict]: Filtered records in order.