🔍 Code Extractor

Search Components

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

Search Results for "embedding"

Found 50 matching component(s)

  • class MyEmbeddingFunction_v1

    A custom embedding function class that generates embeddings for documents using OpenAI's API, with built-in text summarization for long documents and token management.

    File: /tf/active/vicechatdev/OneCo_hybrid_RAG copy.py

    embeddings openai chromadb vector-database text-summarization
  • class SimpleDataHandle

    A data handler class that manages multiple data sources with different types (dataframes, vector stores, databases) and their associated processing configurations.

    File: /tf/active/vicechatdev/OneCo_hybrid_RAG copy.py

    data-management registry vector-store RAG dataframe
  • class OneCo_hybrid_RAG

    A class named OneCo_hybrid_RAG

    File: /tf/active/vicechatdev/OneCo_hybrid_RAG copy.py

    class oneco_hybrid_rag
  • class FixedProjectVictoriaGenerator

    Fixed Project Victoria Disclosure Generator that properly handles all warranty sections.

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

    class fixedprojectvictoriagenerator
  • function publish_document

    Publishes an approved controlled document by converting it to PDF with signatures and audit trail, uploading to FileCloud, and updating the document status to PUBLISHED.

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

    document-management publishing pdf-conversion audit-trail controlled-documents
  • class DocumentDetail

    Document detail view component

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

    class documentdetail
  • class OneCo_hybrid_RAG_v1

    A class named OneCo_hybrid_RAG

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

    class oneco_hybrid_rag
  • class MyEmbeddingFunction_v2

    A custom embedding function class that generates embeddings for text documents using OpenAI's embedding models, with automatic text summarization and token management for large documents.

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

    embeddings openai chromadb text-processing summarization
  • class DocumentProcessor_v5

    Process different document types for RAG context extraction

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

    class documentprocessor
  • class DocumentDetail_v1

    Document detail view component

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

    class documentdetail
  • class ImprovedProjectVictoriaGenerator

    Improved Project Victoria Disclosure Generator with proper reference management.

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

    class improvedprojectvictoriagenerator
  • class OneCo_hybrid_RAG_v2

    A class named OneCo_hybrid_RAG

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

    class oneco_hybrid_rag
  • class ExtensiveSearchManager

    Manages extensive search functionality including full document retrieval, summarization, and enhanced context gathering.

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

    class extensivesearchmanager
  • function generate_simple_html_from_eml

    Converts an email.message.Message object into a clean, styled HTML representation with embedded inline images and attachment listings.

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

    email html-generation email-parsing mime inline-images
  • class ProjectVictoriaDisclosureGenerator

    Main class for generating Project Victoria disclosures from warranty claims.

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

    class projectvictoriadisclosuregenerator
  • class MyEmbeddingFunction

    Custom embedding function class that integrates OpenAI's embedding API with Chroma DB for generating vector embeddings from text documents.

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

    embeddings openai chroma vector-database nlp
  • class MyEmbeddingFunction_v3

    A custom embedding function class that generates embeddings for text documents using OpenAI's embedding models, with automatic text summarization and token limit handling for large documents.

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

    embeddings openai vector-database chromadb text-processing
  • class DocumentProcessor_v6

    Process different document types for RAG context extraction

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

    class documentprocessor
  • function view_document

    Flask route handler that serves documents for in-browser viewing by accepting a file path as a query parameter, validating security constraints, and returning the file with appropriate MIME types and CORS headers.

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

    flask file-serving document-viewer security path-validation
  • function check_configuration

    A comprehensive configuration verification function that checks and displays the status of all DocChat system settings, including API keys, models, ChromaDB connection, directories, and LLM initialization.

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

    configuration verification diagnostics setup validation
  • class DocChatRAG

    Main RAG engine with three operating modes: 1. Basic RAG (similarity search) 2. Extensive (full document retrieval with preprocessing) 3. Full Reading (process all documents)

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

    class docchatrag
  • class DocChatEmbeddingFunction

    A custom ChromaDB embedding function that generates OpenAI embeddings with automatic text summarization for documents exceeding token limits.

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

    embeddings chromadb openai text-processing summarization
  • 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
  • class SignatureImage_v1

    A custom ReportLab Flowable class that renders signature images in PDF documents with automatic fallback to placeholder text when images are unavailable or cannot be loaded.

    File: /tf/active/vicechatdev/document_auditor/src/audit_page_generator.py

    pdf-generation reportlab flowable signature image-rendering
  • class HashGenerator

    A class that provides cryptographic hashing functionality for PDF documents, including hash generation, embedding, and verification for document integrity checking.

    File: /tf/active/vicechatdev/document_auditor/src/security/hash_generator.py

    cryptography hashing SHA-256 PDF document-integrity
  • function load_data_from_chromadb

    Connects to a ChromaDB instance and retrieves all documents from a specified collection, returning them as a list of dictionaries with document IDs, text content, embeddings, and metadata.

    File: /tf/active/vicechatdev/chromadb-cleanup/main.py

    chromadb vector-database data-loading document-retrieval embeddings
  • function save_data_to_chromadb_v1

    Saves a list of document dictionaries to a ChromaDB collection, with support for batch processing, embeddings, and metadata storage.

    File: /tf/active/vicechatdev/chromadb-cleanup/main.py

    chromadb vector-database document-storage embeddings batch-processing
  • function load_data_from_chromadb_v1

    Retrieves all documents from a specified ChromaDB collection, including their IDs, text content, embeddings, and metadata.

    File: /tf/active/vicechatdev/chromadb-cleanup/main copy.py

    chromadb database document-retrieval vector-database embeddings
  • function save_data_to_chromadb

    Saves a list of document dictionaries to a ChromaDB vector database collection, optionally including embeddings and metadata.

    File: /tf/active/vicechatdev/chromadb-cleanup/main copy.py

    chromadb vector-database document-storage embeddings persistence
  • class TextClusterer

    A class that clusters similar documents based on their embeddings using various clustering algorithms (K-means, Agglomerative, DBSCAN) and optionally generates summaries for each cluster.

    File: /tf/active/vicechatdev/chromadb-cleanup/src/clustering/text_clusterer.py

    clustering document-clustering embeddings machine-learning kmeans
  • function calculate_similarity

    Computes the cosine similarity between two embedding vectors, returning a normalized score between 0 and 1 that measures their directional alignment.

    File: /tf/active/vicechatdev/chromadb-cleanup/src/utils/similarity_utils.py

    cosine-similarity vector-comparison embeddings similarity-metric machine-learning
  • function build_similarity_matrix

    Computes a pairwise cosine similarity matrix for a collection of embedding vectors, where each cell (i,j) represents the similarity between embedding i and embedding j.

    File: /tf/active/vicechatdev/chromadb-cleanup/src/utils/similarity_utils.py

    embeddings similarity cosine-similarity matrix nlp
  • function find_similar_documents

    Identifies pairs of similar documents by comparing their embeddings and returns those exceeding a specified similarity threshold, sorted by similarity score.

    File: /tf/active/vicechatdev/chromadb-cleanup/src/utils/similarity_utils.py

    document-similarity embedding-comparison duplicate-detection cosine-similarity nlp
  • class SimilarityCleaner

    A document cleaning class that identifies and removes duplicate or highly similar documents based on embedding vector similarity, keeping only representative documents from each similarity group.

    File: /tf/active/vicechatdev/chromadb-cleanup/src/cleaners/similarity_cleaner.py

    document-processing deduplication similarity embeddings clustering
  • function add_data_section_to_docx

    Adds a data analysis section to a Word document, including analysis metadata, statistical conclusions, and embedded visualizations from saved content or legacy analysis history.

    File: /tf/active/vicechatdev/vice_ai/new_app.py

    document-generation word-document data-analysis visualization report-generation
  • function add_data_section_to_pdf

    Adds a data analysis section to a PDF document story, including analysis metadata, statistical conclusions, and embedded visualizations from saved content or analysis history.

    File: /tf/active/vicechatdev/vice_ai/new_app.py

    pdf-generation reportlab data-analysis document-export visualization
  • class DataAnalysisService

    Service class for managing data analysis operations within document sections, integrating with SmartStat components for statistical analysis, dataset processing, and visualization generation.

    File: /tf/active/vicechatdev/vice_ai/data_analysis_service.py

    data-analysis statistical-analysis session-management dataset-processing visualization
  • class OneCo_hybrid_RAG_v3

    A class named OneCo_hybrid_RAG

    File: /tf/active/vicechatdev/vice_ai/hybrid_rag_engine.py

    class oneco_hybrid_rag
  • class ExtensiveSearchManager_v1

    Manages extensive search functionality including full document retrieval, summarization, and enhanced context gathering.

    File: /tf/active/vicechatdev/vice_ai/hybrid_rag_engine.py

    class extensivesearchmanager
  • class ControlledDocumentApp

    Main application class for the Controlled Document Management System. This class initializes all components and provides the main Panel interface for the application. It is designed to be served via `panel serve` command and integrates with the existing datacapture application.

    File: /tf/active/vicechatdev/CDocs/main.py

    class controlleddocumentapp
  • class SignatureImage

    A ReportLab Flowable subclass for embedding signature images in PDFs with automatic fallback to placeholder text when images are unavailable or cannot be loaded.

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

    reportlab pdf-generation signature flowable image-handling
  • class DocumentDetail_v2

    Document detail view component

    File: /tf/active/vicechatdev/CDocs/ui/document_detail.py

    class documentdetail
  • class UserTasksPanel

    Panel showing pending tasks for the current user

    File: /tf/active/vicechatdev/CDocs/ui/user_tasks_panel.py

    class usertaskspanel
  • class ApprovalPanel_v1

    Approval management interface component

    File: /tf/active/vicechatdev/CDocs/ui/approval_panel_bis.py

    class approvalpanel
  • class ApprovalPanel_v1

    Approval management interface component

    File: /tf/active/vicechatdev/CDocs/ui/approval_panel.py

    class approvalpanel
  • class ReviewPanel_v1

    Review management interface component

    File: /tf/active/vicechatdev/CDocs/ui/review_panel.py

    class reviewpanel
  • class AdminPanel

    Admin configuration interface component

    File: /tf/active/vicechatdev/CDocs/ui/admin_panel.py

    class adminpanel
  • function create_admin_panel

    Factory function that creates and returns a configured AdminPanel instance with optional template, session management, parent application reference, and embedding mode.

    File: /tf/active/vicechatdev/CDocs/ui/admin_panel.py

    factory-pattern admin-panel ui-creation panel dashboard
  • function autoload_js_script

    Generates JavaScript code for autoloading a Bokeh document into a web page element, bundling necessary resources and creating render items for embedding.

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

    bokeh embedding javascript autoload visualization
  • class AutoloadJsHandler

    A custom Tornado request handler that generates and serves the Bokeh autoload JavaScript chunk for embedding Bokeh applications in web pages.

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

    tornado bokeh web-handler javascript autoload

Search Examples