Search - Code Extractor

function validate_and_alternatives

Validates whether a given keyword is a valid chemical compound, biochemical concept, or drug-related term using GPT-4, and returns alternative names/synonyms if valid.

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

validation chemistry biochemistry drug-research llm

class RegulatoryExtractor

A class for extracting structured metadata from regulatory guideline PDF documents using LLM-based analysis and storing the results in an Excel tracking spreadsheet.

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

pdf-extraction regulatory-documents llm-extraction ocr data-extraction

class ReferenceManager_v2

Manages extraction and formatting of references for LLM chat responses. Handles both file references and BibTeX citations, formatting them according to various academic citation styles.

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

class referencemanager

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 SimpleChatMemory

A simple chat memory manager that stores and retrieves conversation history between users and assistants with configurable history limits.

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

chat memory conversation history chatbot

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 main_v59

Entry point function that instantiates a FixedProjectVictoriaGenerator and executes its complete pipeline to generate fixed disclosure documents.

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

entry-point pipeline disclosure-generation orchestration main-function

Base class that contains all static elements of the app Parameters ---------- image : str An Image UID which may be passed on app startup. Immediately redirects to said image Attributes ---------- current_user : Userclass A class containing various information on the user workspace : panel.layout.Column The main container of the app sidebar : panel.layout.Column Container showing items on the side of the app head : panel.layout.Row The header of the app modal : panel.layout.Column The container for the modal window of the app

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

class pathobrowser_base

class ReferenceManager_v3

Manages extraction and formatting of references for LLM chat responses. Handles both file references and BibTeX citations, formatting them according to various academic citation styles.

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

class referencemanager

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 ImprovedProjectVictoriaGenerator

Improved Project Victoria Disclosure Generator with proper reference management.

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

class improvedprojectvictoriagenerator

function main_v63

Entry point function that instantiates an ImprovedProjectVictoriaGenerator and executes its complete pipeline to generate disclosure documents.

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

entry-point main-function disclosure-generation RAG document-generation

class MeetingMinutesGenerator_v1

A class that generates professional meeting minutes from meeting transcripts using either OpenAI's GPT-4o or Google's Gemini AI models.

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

meeting-minutes transcript-processing llm gpt-4o gemini

function main_v16

Command-line interface function that orchestrates the generation of meeting minutes from a transcript file using either GPT-4o or Gemini LLM models.

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

cli command-line meeting-minutes transcript-processing llm

class QueryBasedExtractor_v2

A class that performs targeted information extraction from text using LLM-based query-guided extraction, with support for handling long documents through chunking and token management.

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

information-extraction text-processing llm openai query-based

class ReferenceManager_v4

Manages extraction and formatting of references for LLM chat responses. Handles both file references and BibTeX citations, formatting them according to various academic citation styles.

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

class referencemanager

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

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_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

class pathobrowser_base_v1

Base class that contains all static elements of the app Parameters ---------- image : str An Image UID which may be passed on app startup. Immediately redirects to said image Attributes ---------- current_user : Userclass A class containing various information on the user workspace : panel.layout.Column The main container of the app sidebar : panel.layout.Column Container showing items on the side of the app head : panel.layout.Row The header of the app modal : panel.layout.Column The container for the modal window of the app

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

class pathobrowser_base

function extract_previous_reports_summary

Extracts and summarizes key information from previous meeting report files using document extraction and OpenAI's GPT-4o-mini model to provide context for upcoming meetings.

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

meeting-analysis document-extraction text-summarization llm openai

function test_multiple_files

A test function that validates the extraction of text content from multiple document files using a DocumentExtractor instance, displaying extraction results and simulating combined content processing.

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

testing document-extraction file-processing text-extraction multiple-files

class EnhancedMeetingMinutesGenerator

A class named EnhancedMeetingMinutesGenerator

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

class enhancedmeetingminutesgenerator

function main_v2

Command-line interface function that orchestrates the generation of enhanced meeting minutes from transcript files and PowerPoint presentations using various LLM models (GPT-4o, Azure GPT-4o, or Gemini).

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

cli command-line meeting-minutes llm gpt-4

function process_chat_background

Processes chat requests asynchronously in a background thread, managing RAG engine interactions, progress updates, and session state for various query modes including basic, extensive, full_reading, and deep_reflection.

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

background-processing async rag chat document-retrieval

function api_get_models

Flask API endpoint that returns a list of available LLM models and the default model configuration.

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

api flask rest-api llm configuration

function api_chat

Flask API endpoint that handles chat requests asynchronously, processing user queries through a RAG (Retrieval-Augmented Generation) engine with support for multiple modes, memory, web search, and custom configurations.

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

flask api chat async rag

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 QueryBasedExtractor

A class that extracts relevant information from documents using a small LLM (Language Model), designed for Extensive and Full Reading modes in RAG systems.

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

information-extraction document-processing llm rag query-based

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

function chat

Flask route handler that processes chat requests with RAG (Retrieval-Augmented Generation) capabilities, managing conversation sessions, chat history, and document-based question answering.

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

chat rag retrieval-augmented-generation conversational-ai document-qa

function get_available_models

Flask API endpoint that returns a JSON response containing the list of available LLM models and the default model configured in the application.

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

api endpoint flask llm models

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

function test_config

A test function that validates the presence and correctness of all required configuration settings for a multi-model RAG (Retrieval-Augmented Generation) system.

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

testing validation configuration unit-test assertion

function test_rag_engine

A test function that validates the RAG engine's ability to correctly instantiate different LLM models (OpenAI, Anthropic, Gemini) based on configuration settings.

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

testing rag llm model-switching validation

function main_v40

Test orchestration function that executes a comprehensive test suite for DocChat's multi-LLM model selection feature and reports results.

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

testing integration-tests test-orchestration multi-llm test-runner

class LLMMessage

A simple dataclass that represents a message for Large Language Model (LLM) interactions, containing only the message content as a string.