🔍 Code Extractor

Search Components

Full-Text: Fast keyword matching | Semantic: AI-powered understanding of intent (finds similar concepts)

Search Results for "indexing"

Found 30 matching component(s)

  • function add_document_to_graph_v1

    Creates a Neo4j graph node for a processed document and connects it to a folder hierarchy, along with its text and table chunks.

    File: /tf/active/vicechatdev/offline_docstore_multi_vice.py

    neo4j graph-database document-management knowledge-graph cypher-query

  • class PowerPointProcessor

    A class that processes PowerPoint (.pptx) presentations to extract text content and tables, converting tables to markdown format and organizing content by slides.

    File: /tf/active/vicechatdev/leexi/enhanced_meeting_minutes_generator.py

    powerpoint pptx document-processing text-extraction table-extraction

  • function index_documents_example

    A demonstration function that indexes documents from a specified folder using a DocumentIndexer, creating the folder if it doesn't exist, and displays indexing results and collection statistics.

    File: /tf/active/vicechatdev/docchat/example_usage.py

    document-indexing example tutorial demonstration RAG

  • function main_v46

    Orchestrates and executes a series of example demonstrations for the DocChat system, including document indexing, RAG queries, and conversation modes.

    File: /tf/active/vicechatdev/docchat/example_usage.py

    demo examples orchestration RAG document-chat

  • function build_document_tree_lazy

    Builds a single-level document tree structure for lazy loading, scanning only immediate children of a target directory without recursively loading subdirectories.

    File: /tf/active/vicechatdev/docchat/app.py

    file-system directory-tree lazy-loading document-management file-browser

  • function build_document_tree_recursive

    Recursively builds a complete hierarchical tree structure of documents and folders from a target directory path, filtering for supported file types and skipping hidden/cache directories.

    File: /tf/active/vicechatdev/docchat/app.py

    file-system directory-traversal recursive document-management tree-structure

  • function get_document_info

    Retrieves indexing status and metadata for a document, including whether it's indexed, its document ID, chunk count, and reindexing status.

    File: /tf/active/vicechatdev/docchat/app.py

    document-management indexing metadata vector-database chromadb

  • function init_engines

    Initializes the RAG (Retrieval-Augmented Generation) engine and document indexer components, loads persisted sessions, and optionally starts background auto-indexing of documents.

    File: /tf/active/vicechatdev/docchat/app.py

    initialization RAG document-indexing background-processing threading

  • function api_task_status

    Flask API endpoint that retrieves and returns the status of asynchronous tasks (chat or indexing operations) by task ID.

    File: /tf/active/vicechatdev/docchat/app.py

    api flask rest-endpoint task-status async-polling

  • function api_upload

    Flask API endpoint that handles file uploads, validates file types, saves files to a configured directory structure, and automatically indexes the uploaded document for search/retrieval.

    File: /tf/active/vicechatdev/docchat/app.py

    file-upload api-endpoint document-management rag indexing

  • function api_index_folder

    Flask API endpoint that initiates a background task to index documents in a specified folder, tracking progress and returning a task ID for status monitoring.

    File: /tf/active/vicechatdev/docchat/app.py

    flask api endpoint background-task document-indexing

  • function api_index_progress

    Flask API endpoint that retrieves the current progress status of an asynchronous indexing task by its task ID.

    File: /tf/active/vicechatdev/docchat/app.py

    flask api rest-endpoint progress-tracking async-task

  • function matches_source_filter

    Checks if a document path matches any of the provided source filters using exact match, folder prefix match, path component sequence match, or filename match.

    File: /tf/active/vicechatdev/docchat/rag_engine.py

    path-matching file-filtering document-filtering path-normalization string-matching

  • function upload_document

    Flask route handler that processes file uploads, saves them securely to disk, and indexes the document content for retrieval-augmented generation (RAG) search.

    File: /tf/active/vicechatdev/docchat/blueprint.py

    file-upload document-processing flask-route authentication RAG

  • function index_all_documents

    Flask route handler that initiates background indexing of all documents in the system, creating a task ID for tracking progress and returning immediately while indexing continues asynchronously.

    File: /tf/active/vicechatdev/docchat/blueprint.py

    flask api-endpoint background-task document-indexing async-processing

  • function get_task_status

    Flask API endpoint that retrieves the current status of a background task by its task ID from an in-memory active_tasks dictionary.

    File: /tf/active/vicechatdev/docchat/blueprint.py

    flask api rest-endpoint task-status background-task

  • function get_stats

    Flask API endpoint that retrieves and returns statistics about a document collection from a RAG (Retrieval-Augmented Generation) system.

    File: /tf/active/vicechatdev/docchat/blueprint.py

    flask api endpoint statistics rag

  • class DocumentProcessor_v7

    Process different document types for indexing

    File: /tf/active/vicechatdev/docchat/document_indexer.py

    class documentprocessor

  • class DocumentIndexer

    A class for indexing documents into ChromaDB with support for multiple file formats (PDF, Word, PowerPoint, Excel, text files), smart incremental indexing, and document chunk management.

    File: /tf/active/vicechatdev/docchat/document_indexer.py

    document-indexing vector-database chromadb embeddings pdf-processing

  • function create_test_document

    Creates a text file at the specified path with the given content, primarily used for testing purposes.

    File: /tf/active/vicechatdev/docchat/test_incremental_indexing.py

    testing file-creation test-utilities file-io document-creation

  • function test_incremental_indexing

    Comprehensive test function that validates incremental indexing functionality of a document indexing system, including initial indexing, change detection, re-indexing, and force re-indexing scenarios.

    File: /tf/active/vicechatdev/docchat/test_incremental_indexing.py

    testing incremental-indexing document-indexing integration-test file-system

  • function extract_text_from_pdf

    Extracts all text content from a PDF document and returns it as a string.

    File: /tf/active/vicechatdev/CDocs/utils/pdf_utils.py

    pdf text-extraction document-processing file-io pdf-parsing

  • function process_ellipses

    Expands an Ellipsis (...) in a __getitem__ key by replacing it with the appropriate number of empty slices (slice(None)) to match the dimensions of an object.

    File: /tf/active/vicechatdev/patches/util.py

    indexing ellipsis slicing multi-dimensional data-structures

  • function int_to_alpha

    Converts a non-negative integer to an Excel-style alphabetic column label (A, B, C, ..., Z, AA, AB, ..., ZZ, AAA, etc.).

    File: /tf/active/vicechatdev/patches/util.py

    string-conversion alphabetic-labels excel-columns base-26 spreadsheet

  • function group_select

    Recursively groups a list of key tuples into a nested dictionary structure to optimize indexing operations by avoiding duplicate key lookups.

    File: /tf/active/vicechatdev/patches/util.py

    data-structures optimization indexing grouping recursion

  • function get_spec

    Extracts a specification tuple from a labeled data object, consisting of the class name, group, and label attributes.

    File: /tf/active/vicechatdev/patches/util.py

    metadata specification data-object identification holoviews

  • function cross_index

    Efficiently indexes into a Cartesian product of iterables without materializing the full product, using a linear index to retrieve the corresponding tuple of values.

    File: /tf/active/vicechatdev/patches/util.py

    cartesian-product indexing combinatorics memory-efficient itertools-alternative

  • function search_indices

    Finds the indices of specified values within a source array by using sorted search for efficient lookup.

    File: /tf/active/vicechatdev/patches/util.py

    array-search indexing numpy data-lookup sorting

  • class DynamicMap

    A DynamicMap is a type of HoloMap where the elements are dynamically generated by a callable. The callable is invoked with values associated with the key dimensions or with values supplied by stream parameters.

    File: /tf/active/vicechatdev/patches/spaces.py

    class dynamicmap

  • class GridSpace

    GridSpace is a container class for organizing elements in a 1D or 2D grid structure with floating-point keys, ensuring all contained elements are of the same type.

    File: /tf/active/vicechatdev/patches/spaces.py

    grid layout container mapping 2D-grid

Search Examples