LangChain.Scraper (langchainex v0.2.3)
A Scraper is a GenServer that scrapes natural language text and tries to turn it into some kind of structured data. It comes with a built in "default_scraper" that can generally extract data from text according to the schema you gave it. Examples:
= Scraper.start_link() input_text = "John Doe is 30 years old." {:ok, result} = Scraper.scrape(scraper_pid, input_text)
= Scraper.scrape(scraper_pid, input_text, "default_scraper", %{ output_format: "XML" })
= Scraper.scrape(scraper_pid, input_text, "default_scraper", %{ input_schema: "{ name: { first: String, last: String }, age: Number }", output_format: "YAML" })
Link to this section Summary
Functions
add your own custom scrape chain to the Scraper
Returns a specification to start this module under a supervisor.
Callback implementation for GenServer.init/1.
A default output parser that just returns the first response text as json
Returns a list of all the scrape chains in the Scraper
simple passthrough parser that just returns the result
A default output parser that just returns the first response text
scrape some text using the default scraper
Link to this section Functions
add_scrape_chain(pid, name, scrape_chain)
add your own custom scrape chain to the Scraper
child_spec(init_arg)
Returns a specification to start this module under a supervisor.
See Supervisor.
init(_)
Callback implementation for GenServer.init/1.
json_parser(chain_link, outputs)
A default output parser that just returns the first response text as json
list(pid)
Returns a list of all the scrape chains in the Scraper
output_parser(result)
simple passthrough parser that just returns the result
passthru_parser(chain_link, response_text)
A default output parser that just returns the first response text
scrape(pid, input_text, llm_pid, name \\ "default_scraper", opts \\ %{})
scrape some text using the default scraper