2023-03-22 22:00:44 +00:00
|
|
|
# Extraction
|
|
|
|
|
|
|
|
|
|
Most APIs and databases still deal with structured information.
|
|
|
|
|
Therefore, in order to better work with those, it can be useful to extract structured information from text.
|
|
|
|
|
Examples of this include:
|
|
|
|
|
|
|
|
|
|
- Extracting a structured row to insert into a database from a sentence
|
|
|
|
|
- Extracting multiple rows to insert into a database from a long document
|
|
|
|
|
- Extracting the correct API parameters from a user query
|
|
|
|
|
|
2023-06-20 21:06:50 +00:00
|
|
|
This work is extremely related to [output parsing](/docs/modules/model_io/output_parsers/).
|
2023-03-22 22:00:44 +00:00
|
|
|
Output parsers are responsible for instructing the LLM to respond in a specific format.
|
|
|
|
|
In this case, the output parsers specify the format of the data you would like to extract from the document.
|
|
|
|
|
Then, in addition to the output format instructions, the prompt should also contain the data you would like to extract information from.
|
|
|
|
|
|
|
|
|
|
While normal output parsers are good enough for basic structuring of response data,
|
|
|
|
|
when doing extraction you often want to extract more complicated or nested structures.
|
|
|
|
|
For a deep dive on extraction, we recommend checking out [`kor`](https://eyurtsev.github.io/kor/),
|
|
|
|
|
a library that uses the existing LangChain chain and OutputParser abstractions
|
|
|
|
|
but deep dives on allowing extraction of more complicated schemas.
|
