{"object":"list","q":"parsing","limit":10,"section":"docs","results":[{"title":"Create Files","url":"/docs/stores/store-files","description":"Parsing Strategy","score":null,"section":"docs"},{"title":"Concepts","url":"/docs/concepts","description":"If parsing fails, the file ends up in a `failed` state instead of `completed`. The specific error is available on `last_error`.","score":null,"section":"docs"},{"title":"Data Models","url":"/docs/stores/data-models","description":"† The `summary`, `ocr_text` and `transcription` fields are only populated when the file was ingested with the `high_quality` parsing strategy.","score":null,"section":"docs"},{"title":"Generated Metadata","url":"/docs/stores/store-files/generated-metadata","description":"With the `high_quality` parsing strategy, an audio file or a video with an audio track is transcribed as a whole, and every word is attributed to a speaker. Speakers are numbered in the order they first speak, and a label means the same person in every chunk of the file, so you can filter on `generated_metadata.speake…","score":null,"section":"docs"},{"title":"Manage Files","url":"/docs/stores/store-files/manage-store-files","description":"**File Metadata vs. Chunk Metadata**: `metadata` is your file-level metadata and is shared across all chunks from that file. `generated_metadata` is produced during parsing and can differ for each chunk.","score":null,"section":"docs"},{"title":"Changelog","url":"/docs/changelog","description":"HTML files are now parsed as documents instead of code. Search results return the page's content as clean Markdown, with headings, tables, and links but no markup or navigation, ready to pass to an LLM. You are billed for the extracted text, not the page source, which makes HTML ingestion cheaper.","score":null,"section":"docs"}]}