PBIFORGE

The downloaded.pbitopens in Power BI Desktop, prompts for any data-source credentials, and renders the dashboard.

ReportForge always runs the deterministic dashboard builder (KPI cards, headline bar/line chart, donut for low-cardinality dims, second "Breakdowns" page when the dataset is rich). On top of that, if you supply an LLM key, your prompt is interpreted and additional visuals are appended.

- Your prompt
- Column names + roles (measure/dimension)
- Column semantic types (temporal,geographic,categorical, etc.)
- Visuals the deterministic builder already produced (so it doesn't duplicate them)

What it does NOT see: any of your data rows.

The model returns a JSON list of chart specs (type, x-axis column, y-axis column, title); ReportForge validates each spec against the column profile and adds the ones that pass.

The response headerX-ReportForge-Parsertells you which path ran for any given generate (llm:anthropic,llm:openai,llm:qwen,llm:<provider>-empty,no-key, ordeterministic-only). The UI shows this under each "Report ready" message.

ReportForge ships withlazydriver imports — the base install works for CSV-only use. Install drivers only for the databases you need:

# SQL Server (also needs the Microsoft ODBC Driver 17 or 18, installed system-wide) .\.venv\Scripts\python.exe -m pip install pyodbc # PostgreSQL .\.venv\Scripts\python.exe -m pip install psycopg2-binary # Oracle (thin mode - no Oracle client install required) .\.venv\Scripts\python.exe -m pip install oracledb

In the UI, pick the source kind from theData sourcedropdown. ReportForge:
- Connects with the credentials you supply.
- PullsSELECT TOP 1000(orLIMIT 1000) to profile column types, cardinality, and roles.
- Generates a Power Query M expression that Power BI Desktop will use to fetch thefulldataset live.
- Compiles everything into a.pbit.

The credentials never make it into the.pbitfile — Power BI Desktop will prompt for sign-in on first open. This is the standard Power BI Template behavior.

Paste aSELECT(with joins, filters, anything) into theOr: SELECT querybox. ReportForge will profile the first 1000 rows of the result and target the same query in the generated M.

- Your prompt
- The list of column names + their inferred roles
- The list of visuals already generated by the deterministic builder
- Nothing else.Your data rows never leave your machine.

The key is cached in the browser tab'ssessionStorageso you don't have to re-paste it on every generate. It's wiped when the tab closes.

For local Qwen, chooseLocal Qwen 2.5 (Ollama)in the provider dropdown. The Windows installer bundles a CPU-only Ollama runtime and will start it when ReportForge launches;qwen2.5:3bis pulled on first use if it is missing, so the first Qwen generation can take a few minutes and needs internet access. ReportForge callshttp://127.0.0.1:11434by default; override withQWEN_OLLAMA_URLorOLLAMA_HOSTif your Ollama server runs elsewhere.

If you skip the key, ReportForge falls back to the deterministic dashboard builder only. Your prompt has no effect in that case — the dashboard is built purely from the column profile.

Drop any PNG/JPG (a screenshot of a dashboard you like, a brand mockup, a Tableau page). ReportForge runs two extractions in parallel:

Layout extraction (Claude Vision, requires Anthropic key)Reads the structural layout of the reference dashboard:

- How many KPI/metric cards are visible → used as the KPI card count in the generated report
- Which chart types are present (bar, column, line, area, donut, etc.) → influences chart type selection
- Whether a right-side filter/slicer panel exists → adds or omits a slicer panel
- Whether the KPI cards are in a left-column rail or a top-row grid → picks the matching layout template

Palette extraction (Claude Vision, or local Pillow fallback)Extracts the color scheme:

- Primary, secondary, and accent colors
- Page canvas background
- Chart series palette (8-color rotation)

The layout extraction requires anANTHROPIC_API_KEY. If no key is available, ReportForge still samples colors locally with Pillow and the layout falls back to the data-driven default.

All endpoints are local-only (127.0.0.1:8000).

Windows installer (single .exe for end users)

┌──────────────┐ CSV / SQL → ┤ data_profiler / data_sources ┤ → DatasetProfile └──────────────┘ │ ▼ build_intent_from_profile (deterministic) │ │ + prompt parser (regex OR LLM) │ + image layout hint extractor (Claude Vision) │ + image palette extractor (Claude Vision / Pillow) ▼ ReportIntent (Pydantic) │ ▼ build_bim_from_profile → semantic model (BIM JSON) build_m_for_source → Power Query M build_layout_from_intent → report layout (visuals + theme) │ ▼ pbi-tools.core compile → .pbit inject_data_mashup (DataMashup binary) inject_report_layout (Report/Layout) │ ▼ .pbit file

- main.py— FastAPI app, endpoints, static UI mount.
- orchestrator.py— pipelines (pipeline_from_csv,pipeline_from_source).
- data_profiler.py— CSV profiler.
- data_sources.py— DB profilers + M generators for MSSQL / Postgres / Oracle.
- auto_intent.py— deterministic intent + layout builder, regex prompt parser.
- llm_intent.py— LLM-driven prompt parser (Anthropic + OpenAI).
- image_analyzer.py— palette extraction and layout hint extraction from reference images.
- file_writer.py— writes the project tree, injects DataMashup + Report/Layout.
- mcp_server.py— MCP tools for Claude Desktop.
- static/index.html— browser UI.

.pbitwon't open / "An error occurred while opening the file".Usually a stale generation ingenerated_reports/. Delete and regenerate. If it persists, check the server logs —pbi-tools.coreerrors usually show up there.

External Tools button doesn't appear in Power BI Desktop.Most often a Fabric tenant policy. See the troubleshooting section inEXTERNAL_TOOL_SETUP.md.

LLM call fails silently.When the LLM call errors or returns an empty visuals list, ReportForge falls back to the deterministic builder and surfacesllm:<provider>-emptyin theX-ReportForge-Parserresponse header (visible in the UI status message). Double-check the key value, the provider dropdown, and thatopenaiis installed (pip install openai) if you picked OpenAI.

Generation succeeds but the dashboard looks plain blue, not like my reference image.The local Pillow palette extractor is more conservative than the Anthropic vision path. If you have anANTHROPIC_API_KEYset, the vision path gives better color results. Or open the resulting.pbitand tweak the theme manually.

Reference image supplied but the layout doesn't match it.Layout extraction requires anANTHROPIC_API_KEY— without one, only colors are sampled and the layout falls back to the data-driven default. Check that the key is set and that the reference image clearly shows the dashboard structure (card tiles, chart panels, filter sidebar).

This is the local-first incarnation of ReportForge. Railway deployment isnotthe supported path right now — everything is designed to run on your machine, talk to local CSVs and databases, and write.pbitfiles intogenerated_reports/.

The roadmap (see.claude/plans/) covers:

- Phase 1: SQL connectors (✅ this release).
- Phase 2: joined multi-table models with auto-relationship inference.
- Phase 3: read the model out of an open Power BI Desktop session via a .NET helper.

Query databases, build dashboards, and analyze documents in natural language from Claude or any MCP client. 28+ tools, 70+ data sources.

Manage Apache Superset datasets, metrics, and SQL queries.

A suite of tools for developers to build AI applications that integrate with Tableau.

Connects Claude Desktop to Tableau Server, enabling natural language interactions with your Tableau data and administrative capabilities.

Interact with Tableau Server using natural language to query data and perform administrative tasks.

Analyze and manage traffic, funnels, cohorts, revenue, errors

EU Corporate Sustainability Reporting Directive compliance — ESRS mapping, double materiality, ESG data collection by MEOK AI Labs

EU Corporate Sustainability Reporting Directive compliance — ESRS data points, double materiality assessments, audit trails, and XBRL-ready outputs for ESG reporting.

Analyzes manufacturing production capacity, including evaluations, equipment, processes, and factory distribution to assess enterprise strength.