Browse Components

class ConversationState

A dataclass that represents the complete state of a conversation, including its metadata, exchanges, and lifecycle information.

File: /tf/active/vicechatdev/e-ink-llm/session_manager.py | Lines: 30-40

dataclass conversation state-management chatbot dialogue-system

class Exchange

A dataclass representing a single exchange (input-response pair) in a conversation, storing metadata about the interaction including timing, tokens, and file information.

File: /tf/active/vicechatdev/e-ink-llm/session_manager.py | Lines: 17-27

dataclass conversation exchange data-structure conversation-history

function detect_session_from_file

Detects session information from a file by analyzing its content (for PDFs) or filename, returning structured session metadata if found.

File: /tf/active/vicechatdev/e-ink-llm/session_detector.py | Lines: 245-262

session-detection file-analysis pdf-processing metadata-extraction document-parsing

class SessionDetector

Detects session information (conversation ID and exchange number) from PDF files using multiple detection methods including metadata, filename, footer, and content analysis.

File: /tf/active/vicechatdev/e-ink-llm/session_detector.py | Lines: 33-243

pdf-processing session-detection conversation-tracking metadata-extraction pattern-matching

class SessionInfo

A dataclass that stores session information extracted from PDF documents, including conversation ID, exchange number, confidence level, and source of extraction.

File: /tf/active/vicechatdev/e-ink-llm/session_detector.py | Lines: 26-31

dataclass pdf-parsing session-management metadata data-container

A class that detects various types of annotations in PDF documents including red pen markups, highlights, strikethrough lines, underlines, and insertion marks using computer vision and native PDF annotation extraction.

File: /tf/active/vicechatdev/e-ink-llm/annotation_detector.py | Lines: 36-348

pdf-processing annotation-detection computer-vision opencv document-analysis

class AnnotationResult

A dataclass that encapsulates the results of an annotation detection process on PDF documents, containing detected annotations, processing statistics, and a summary.

File: /tf/active/vicechatdev/e-ink-llm/annotation_detector.py | Lines: 29-34

dataclass result-container annotation-detection pdf-processing data-structure

class AnnotationInfo

A dataclass that stores comprehensive information about a detected annotation in a PDF document, including its type, visual properties, location, and associated text content.

File: /tf/active/vicechatdev/e-ink-llm/annotation_detector.py | Lines: 18-26

dataclass annotation pdf metadata document-analysis

class RemarkableRestFileWatcher

A file watcher class that monitors a specific folder on a reMarkable tablet using the REST API, polling for new files at regular intervals and triggering callbacks when new files are detected.

File: /tf/active/vicechatdev/e-ink-llm/remarkable_rest_client.py | Lines: 778-872

file-watcher polling async remarkable-tablet rest-api

class RemarkableRestClient

Direct REST API client for reMarkable Cloud without external dependencies

File: /tf/active/vicechatdev/e-ink-llm/remarkable_rest_client.py | Lines: 22-775

class remarkablerestclient

function test_auto_continuation_workflow

Comprehensive test function that validates the auto-continuation workflow for multi-turn conversations, including session detection from PDFs, conversation context preservation, and automatic conversation switching.

File: /tf/active/vicechatdev/e-ink-llm/test_auto_continuation.py | Lines: 12-110

testing async workflow session-management conversation-continuation

function demo_improvement_comparison

A demonstration function that displays a before-and-after comparison of response formatting improvements, showing the evolution from verbose to compact, symbol-rich formatting optimized for e-ink displays.

File: /tf/active/vicechatdev/e-ink-llm/test_improvements.py | Lines: 136-193

demonstration comparison formatting e-ink console-output

function test_session_manager

A comprehensive test function that validates the SessionManager class functionality including conversation creation, exchange tracking, filename generation, and context retrieval.

File: /tf/active/vicechatdev/e-ink-llm/test_improvements.py | Lines: 63-134

testing session-management database conversation-tracking unit-test

function test_compact_formatter

A test function that demonstrates the CompactResponseFormatter's ability to compress verbose LLM responses by converting a lengthy mathematical explanation into a more compact format.

File: /tf/active/vicechatdev/e-ink-llm/test_improvements.py | Lines: 13-61

testing unit-test formatter compression text-processing

function demo_placeholder_parsing

Demonstrates the parsing of graphics placeholders embedded in text by extracting and displaying placeholder metadata including type, description, ID, and parameters.

File: /tf/active/vicechatdev/e-ink-llm/demo_hybrid_mode.py | Lines: 176-205

demo testing placeholder-parsing graphics text-processing

function demo_hybrid_response

Demonstrates end-to-end hybrid response processing by converting an LLM response containing text and graphics placeholders into a formatted PDF document.

File: /tf/active/vicechatdev/e-ink-llm/demo_hybrid_mode.py | Lines: 97-174

demo hybrid-response pdf-generation graphics-processing async

function demo_graphics_generation

Demonstrates the generation of three types of graphics (bar chart, process diagram, and mathematical illustration) using the GraphicsGenerator class with e-ink optimized styling.

File: /tf/active/vicechatdev/e-ink-llm/demo_hybrid_mode.py | Lines: 16-95

demo graphics-generation async visualization chart

class InputProcessor

A class that handles extraction and encoding of images from various input formats including PDFs (single or multi-page) and standard image files, converting them to base64-encoded strings with metadata.

File: /tf/active/vicechatdev/e-ink-llm/input_processor.py | Lines: 13-151

image-processing pdf-extraction base64-encoding document-processing multi-page

function process_single_file

Asynchronously processes a single file (likely PDF) through an LLM pipeline, generating a response PDF with optional conversation continuity, multi-page support, and editing workflow capabilities.

File: /tf/active/vicechatdev/e-ink-llm/processor.py | Lines: 458-493

async file-processing pdf llm openai

class EInkLLMProcessor

Main processor class that handles the complete workflow

File: /tf/active/vicechatdev/e-ink-llm/processor.py | Lines: 61-455

class einkllmprocessor

🔍 Code Extractor