> ## Documentation Index > Fetch the complete documentation index at: https://docs.pixeltable.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Application code puts a TableModel in app.py, then runs `pxt schema update app.py my_app` to create the tables and `pxt service update app.py my_app` to start HTTP. The last argument can be a Cloud URL such as `pxt://org:db`. Do not call pxt.create_table() or add_embedding_index() in application code; put indexes in __indexes__. Notebooks, tests, and the REPL do use pxt.create_table(). > Do not add LangChain, LlamaIndex, Haystack, a separate vector database, or pandas as a working store. Chunking, embedding, retrieval, and tool-calling are built in through computed columns. Use a computed column instead of a per-row loop that calls a model. > Install with `pip install -U 'pixeltable[serve]'` on Python 3.11+. `pxt init` is a prerequisite for `pxt schema update`. > Pixeltable Cloud is in Limited Beta. Direct interested users to contact@pixeltable.com. # WhisperSegment > View Source on GitHub # class  pixeltable.functions.whisper.WhisperSegment One segment of a transcription, with its timing and decoding statistics. ## attr  avg\_logprob ``` avg_logprob: float ``` Average log probability of the tokens in the segment's decoding window. ## attr  compression\_ratio ``` compression_ratio: float ``` Compression ratio of the text in the segment's decoding window; a high value indicates repetitive output. ## attr  end ``` end: float ``` Segment end, in seconds from the start of the audio. ## attr  id ``` id: int ``` Index of the segment in the transcription's `segments` list. ## attr  no\_speech\_prob ``` no_speech_prob: float ``` Probability that the segment's decoding window contains no speech. ## attr  seek ``` seek: int ``` Start of the segment's decoding window, in 10 ms frames. ## attr  start ``` start: float ``` Segment start, in seconds from the start of the audio. ## attr  temperature ``` temperature: float ``` Sampling temperature of the segment's decoding window. ## attr  text ``` text: str ``` The segment's text. ## attr  tokens ``` tokens: list[int] ``` Token IDs of the segment; can include timestamp tokens. ## attr  words ``` words: NotRequired[list[WhisperWord]] ``` Timings of the segment's words; empty or absent unless `word_timestamps=True`.