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

IronClaw is constrained by the use of TEE credential vault for security.

Architectural pattern for semantic boundary detection using Python libraries (python-docx, python-pptx) and JSON for table embedding, enabling better document structure preservation.

Text chunk storage persists extracted text chunks including DOCX and PPTX chunks into the DuckDB database's doc_text_chunks table.

TextToSQLService converts natural language questions into SQL queries using LLMs, building prompts with schema info and parsing responses for execution. QuestionRouter uses TextToSQLService for generating SQL from natural language queries on the structured path. TextToSQLService integrates with Ollama LLM by calling its generate API on qwen3-coder-next model to generate SQL queries. QuestionRouter uses TextToSQLService for generating SQL from natural language queries on the structured path. TextToSQLService integrates with Ollama LLM by calling its generate API on qwen3-coder-next model to generate SQL queries. TextToSQLService depends on IronClawClient integration for agent logic involving SQL generation. QuestionRouter depends on TextToSQLService to convert natural language queries to SQL. DataLens Development uses TextToSQLService which connects to Ollama for generating SQL from natural language queries. TextToSQLService enables QueryDataSkill to convert natural language queries to SQL queries. Text-to-SQL Service is defined in backend/app/services/text_to_sql.py. The generate_sql method is part of the Text-to-SQL Service.

Utilized alongside PyTorch for NLP tasks within the GPU-based document extraction pipeline.

The Frontend uses TypeScript as a core technology for type safety.

For enterprise multi-tenant scaling, DataLens requires adding a UserResolver component to extract identity from authentication. DataLens requires adding UserResolver for multi-tenant user permissions. DataLens needs UserResolver to add multi-tenant permissions like Vanna

API endpoint is likely affected by uvicorn module cache causing KeyError:0 bug FastAPI depends on Uvicorn for serving the application.

Vanna is a lightweight AI platform used for autonomous data extraction, planning, verification, and iterative refinement, all running locally with Ollama models like qwen3-coder-next. It supports fast, zero-cost inference on shared GPU hardware. Vanna depends on qdrant-client for vector database integration.

The plan includes a Verifier agent to check data quality after extraction.

DS-STAR Intelligence includes the VerifierAgent component. Verifier Agent is part of the plan, serving as an LLM-judge to check data completeness, accuracy, and consistency. VerifierAgent is included in the DS-STAR pipeline. DS-STAR Orchestrator includes VerifierAgent as part of its iterative refinement loop DSStarOrchestrator incorporates the verifier agent for quality scoring of extraction DS-STAR Orchestrator includes VerifierAgent as part of its iterative refinement loop DSStarOrchestrator incorporates the verifier agent for quality scoring of extraction DS-STAR Intelligence capability includes the VerifierAgent component responsible for quality assessment and LLM-judge functionality. The DS-STAR pipeline includes the VerifierAgent component. The Verifier Agent operates within the plan to check data quality and extraction completeness. Router Agent uses outputs from Verifier Agent to decide extraction plan adjustments.

npm dependency: vite@^7.3.1, used in frontend, version 7.3.1, license type unspecified, no approval or risk assessment noted.

GPU Infrastructure requires deployment of vLLM with Qwen2.5-Coder-14B-AWQ model. The implementation plan includes the vLLM component for GPU infrastructure. GPU Infrastructure uses vLLM for large language model execution on elin. The vLLM component uses the Qwen2.5-Coder-14B-AWQ model version. The plan uses vLLM for large language model inference on elin GPU.

The Docker deployment includes volumes configurations for persistent storage. The Docker deployment configures volumes for data persistence

IronClaw incorporates WASM sandboxing as a technical constraint for tool isolation.