The Docker deployment includes Redis Rq depends on redis as the message broker for job queueing.

The command-line interface for Redis, used throughout the project to monitor and manage the job queue; recent sessions confirmed its version is compatible and operational, supporting reliable task queuing and progress tracking.

Qdrant-client uses requests for HTTP communications.

Router agent manages fixes and extensions to the extraction plan.

DataLens Development applies the Router Architecture for modular endpoint routing and domain separation.

DS-STAR Intelligence includes the RouterAgent component. Router Agent decides between fixing and extending steps, managing the iteration loop in the plan. RouterAgent is part of the DS-STAR pipeline. DS-STAR Orchestrator uses RouterAgent for decision logic in its process DSStarOrchestrator uses router agent for decision making in the extraction process DS-STAR Orchestrator uses RouterAgent for decision logic in its process DSStarOrchestrator uses router agent for decision making in the extraction process The DS-STAR pipeline includes the RouterAgent component. DS-STAR Intelligence contains the RouterAgent component. The Router Agent manages iteration loops in the DS-STAR planning process as per the plan. The DS-STAR Intelligence Layer includes the RouterAgent component. DS-STAR Intelligence includes the RouterAgent that makes decision logic for extraction steps. DS-STAR Intelligence includes the RouterAgent component which manages decision logic such as FIX, ADD, or PROCEED. Router Agent uses outputs from Verifier Agent to decide extraction plan adjustments.

RQ is a background job management tool used for tasks like schema profiling and session warming, though details are limited in the messages. The Batch Upload process uses the RQ job queue for reliable background job execution. The RQ job queue manages the execution of the extract_file_job() function with a timeout for large files. The Batch Upload process uses the RQ job queue for reliable background job execution. The RQ job queue manages the execution of the extract_file_job() function with a timeout for large files. AI Summary Generation is implemented asynchronously using the RQ job queue to avoid blocking HTTP responses during file list retrieval. Vectorize Progress Tracking uses the RQ job queue to track status and progress of asynchronous embedding jobs. Vectorize Progress Tracking queries the RQ job queue and chunk counts to provide accurate vectorization progress percentages. The RQ worker for async job processing consumes jobs from the RQ job queue to generate AI summaries and process embeddings asynchronously. The RQ worker depends on the RQ job queue to receive tasks for async AI summary generation and embedding processing. Background workers use RQ job chaining for job chaining and orchestration. Background workers utilize RQ job chaining to coordinate sequential processing tasks.

Rq depends on redis as the message broker for job queueing.

Schema Limiting constrains Arctic-Text2SQL-R1-7B to reduce the number of database tables provided for each query to avoid context window overflow. Phase 1 Implementation includes reducing the maximum number of tables passed to SQL generator via Schema Limiting to avoid Arctic context overflow.

The DiscoveryFlow component is built with the shadcn stack, enabling modern UI features like gradients and animations.

Contains skills related to data extraction and processing, details not specified.

The smart auto-processing pipeline uses Qdrant for vector search functionality within DataLens. The smart processing capability involves Phase B, which is a smart auto-processing pipeline with Qdrant. The smart processing capability involves Phase B, which is a smart auto-processing pipeline with Qdrant.

DataLens uses the Sonnet model strategy as the default for data analysis work. Phase 2 Strategy Research & Decision Point involves the use of Sonnet 4.6 agent for generating PHASE2_IMPLEMENTATION_PLAN.md document The Sonnet subagent builds GPU-first extractors that make Docling mandatory with no fallback options. DataLens agent uses the Sonnet model as its primary LLM for data analysis work requiring high quality.

The DataLens backend depends on SQL migration files to create and update necessary database tables, including those for agent features. Alembic can be used to manage SQL migration files for database schema evolution in DataLens.

The platform prioritizes SQL-first queries to allow direct, optimized SQL execution, enhancing flexibility and performance in data analysis. The design decision to accept raw SQL queries (SQL-first queries) is implemented in DataLens Development to prioritize working end-to-end flow.

The DataLens Platform uses SQLAlchemy to interact with the PostgreSQL schema for database operations. SQLAlchemy depends on psycopg2-binary as a PostgreSQL database driver. Alembic depends on SQLAlchemy for database migrations.

The FastAPI backend in the DataLens Project uses SQLAlchemy ORM for data access. The Backend uses SQLAlchemy ORM as a third-party component for database interaction.

StreamingResponse wraps the agent.py event_generator() function to stream data asynchronously to the client.

The DiscoveryFlow component is implemented using the Svelte framework. The npm dev dependency @sveltejs/adapter-auto depends on svelte in the frontend project. The npm dev dependency @sveltejs/adapter-node depends on svelte in the frontend project. The npm dev dependency shadcn-svelte depends on svelte in the frontend project dependencies.

The Frontend is implemented using Svelte 5 framework compatible with production deployment.

The BulkUpload component uses Svelte 5 runes for its frontend implementation.

npm dependency: svelte-check@^4.3.6, used in frontend, version 4.3.6, license type and approval status unspecified.

Docling was selected over TableGPT2 for the SVGV Budget Analysis Project due to better suitability and accuracy for Excel extraction without GPU requirements. TableGPT2 was evaluated but rejected in favor of Docling for Excel file extraction due to older technology and less fitting use case.

The Frontend utilizes Tailwind CSS The npm dev dependency tailwind-merge depends on tailwindcss as part of the frontend tooling.