2 Commits

Author	SHA1	Message	Date
MkDev11	6f8858b1a6	feat/Add AI-Powered Bank Statement Import (step 1, PDF import & analysis) (#808) ... * feat: Add PDF import with AI-powered document analysis This enhances the import functionality to support PDF files with AI-powered document analysis. When a PDF is uploaded, it is processed by AI to: - Identify the document type (bank statement, credit card statement, etc.) - Generate a summary of the document contents - Extract key metadata (institution, dates, balances, transaction count) After processing, an email is sent to the user asking for next steps. Key changes: - Add PdfImport model for handling PDF document imports - Add Provider::Openai::PdfProcessor for AI document analysis - Add ProcessPdfJob for async PDF processing - Add PdfImportMailer for user notification emails - Update imports controller to detect and handle PDF uploads - Add PDF import option to the new import page - Add i18n translations for all new strings - Add comprehensive tests for the new functionality * Add bank statement import with AI extraction - Create ImportBankStatement assistant function for MCP - Add BankStatementExtractor with chunked processing for small context windows - Register function in assistant configurable - Make PdfImport#pdf_file_content public for extractor access - Increase OpenAI request timeout to 600s for slow local models - Increase DB connection pool to 20 for concurrent operations Tested with M-Pesa bank statement via remote Ollama (qwen3:8b): - Successfully extracted 18 transactions - Generated CSV and created TransactionImport - Works with 3000 char chunks for small context windows * Add pdf-reader gem dependency The BankStatementExtractor uses PDF::Reader to parse bank statement PDFs, but the gem was not properly declared in the Gemfile. This would cause NameError in production when processing bank statements. Added pdf-reader ~> 2.12 to Gemfile dependencies. * Fix transaction deduplication to preserve legitimate duplicates The previous deduplication logic removed ALL duplicate transactions based on [date, amount, name], which would drop legitimate same-day duplicates like multiple ATM withdrawals or card authorizations. Changed to only deduplicate transactions that appear in consecutive chunks (chunking artifacts) while preserving all legitimate duplicates within the same chunk or non-adjacent chunks. * Refactor bank statement extraction to use public provider method Address code review feedback: - Add public extract_bank_statement method to Provider::Openai - Remove direct access to private client via send(:client) - Update ImportBankStatement to use new public method - Add require 'set' to BankStatementExtractor - Remove PII-sensitive content from error logs - Add defensive check for nil response.error - Handle oversized PDF pages in chunking logic - Remove unused process_native and process_generic methods - Update email copy to reflect feature availability - Add guard for nil document_type in email template - Document pdf-reader gem rationale in Gemfile Tested with both OpenAI (gpt-4o) and Ollama (qwen3:8b): - OpenAI: 49 transactions extracted in 30s - Ollama: 40 transactions extracted in 368s - All encapsulation and error handling working correctly * Update schema.rb with ai_summary and document_type columns * Address PR #808 review comments - Rename :csv_file to :import_file across controllers/views/tests - Add PDF test fixture (sample_bank_statement.pdf) - Add supports_pdf_processing? method for graceful degradation - Revert unrelated database.yml pool change (600->3) - Remove month_start_day schema bleed from other PR - Fix PdfProcessor: use .strip instead of .strip_heredoc - Add server-side PDF magic byte validation - Conditionally show PDF import option when AI provider available - Fix ProcessPdfJob: sanitize errors, handle update failure - Move pdf_file attachment from Import to PdfImport - Document deduplication logic limitations - Fix ImportBankStatement: catch specific exceptions only - Remove unnecessary require 'set' - Remove dead json_schema method from PdfProcessor - Reduce default OpenAI timeout from 600s to 60s - Fix nil guard in text mailer template - Add require 'csv' to ImportBankStatement - Remove Gemfile pdf-reader comment * Fix RuboCop indentation in ProcessPdfJob * Refactor PDF import check to use model predicate method Replace is_a?(PdfImport) type check with requires_csv_workflow? predicate that leverages STI inheritance for cleaner controller logic. * Fix missing 'unknown' locale key and schema version mismatch - Add 'unknown: Unknown Document' to document_types locale - Fix schema version to match latest migration (2026_01_24_180211) * Document OPENAI_REQUEST_TIMEOUT env variable Added to .env.local.example and docs/hosting/ai.md * Rename ALLOWED_MIME_TYPES to ALLOWED_CSV_MIME_TYPES for clarity * Add comment explaining requires_csv_workflow? predicate * Remove redundant required_column_keys from PdfImport Base class already returns [] by default * Add ENV toggle to disable PDF processing for non-vision endpoints OPENAI_SUPPORTS_PDF_PROCESSING=false can be used for OpenAI-compatible endpoints (e.g., Ollama) that don't support vision/PDF processing. * Wire up transaction extraction for PDF bank statements - Add extracted_data JSONB column to imports - Add extract_transactions method to PdfImport - Call extraction in ProcessPdfJob for bank statements - Store transactions in extracted_data for later review * Fix ProcessPdfJob retry logic, sanitize and localize errors - Allow retries after partial success (classification ok, extraction failed) - Log sanitized error message instead of raw message to avoid data leakage - Use i18n for user-facing error messages * Add vision-capable model validation for PDF processing * Fix drag-and-drop test to use correct field name csv_file * Schema bleedover from another branch * Fix drag-drop import form field name to match controller * Add vision capability guard to process_pdf method --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: mkdev11 <jaysmth689+github@users.noreply.github.com> Co-authored-by: Juan José Mata <jjmata@jjmata.com>	2026-01-30 20:44:25 +01:00
Carlos Adames	b56dbdb9eb	Feat: /import endpoint & drag-n-drop imports (#501) ... * Implement API v1 Imports controller - Add Api::V1::ImportsController with index, show, and create actions - Add Jbuilder views for index and show - Add integration tests - Implement row generation logic in create action - Update routes * Validate import account belongs to family - Add validation to Import model to ensure account belongs to the same family - Add regression test case in Api::V1::ImportsControllerTest * updating docs to be more detailed * Rescue StandardError instead of bare rescue in ImportsController * Optimize Imports API and fix documentation - Implement rows_count counter cache for Imports - Preload rows in Api::V1::ImportsController#show - Update documentation to show correct OAuth scopes * Fix formatting in ImportsControllerTest * Permit all import parameters and fix unknown attribute error * Restore API routes for auth, chats, and messages * removing pr summary * Fix trailing whitespace and configured? test failure - Update Import#configured? to use rows_count for performance and consistency - Mock rows_count in TransactionImportTest - Fix trailing whitespace in migration * Harden security and fix mass assignment in ImportsController - Handle type and account_id explicitly in create action - Rename import_params to import_config_params for clarity - Validate type against Import::TYPES * Fix MintImport rows_count update and migration whitespace - Update MintImport#generate_rows_from_csv to update rows_count counter cache - Fix trailing whitespace and final newline in AddRowsCountToImports migration * Implement full-screen Drag and Drop CSV import on Transactions page - Add DragAndDropImport Stimulus controller listening on document - Add full-screen overlay with icon and text to Transactions index - Update ImportsController to handle direct file uploads via create action - Add system test for drag and drop functionality * Implement Drag and Drop CSV upload on Import Upload page - Add drag-and-drop-import controller to import/uploads/show - Add full-screen overlay to import/uploads/show - Annotate upload form and input with drag-and-drop targets - Add PR_SUMMARY.md * removing pr summary * Add file validation to ImportsController - Validate file size (max 10MB) and MIME type in create action - Prevent memory exhaustion and invalid file processing - Defined MAX_CSV_SIZE and ALLOWED_MIME_TYPES in Import model * Refactor dragLeave logic with counter pattern to prevent flickering * Extract shared drag-and-drop overlay partial - Create app/views/imports/_drag_drop_overlay.html.erb - Update transactions/index and import/uploads/show to use the partial - Reduce code duplication in views * Update Brakeman and harden ImportsController security - Update brakeman to 7.1.2 - Explicitly handle type assignment in ImportsController#create to avoid mass assignment - Remove :type from permitted import parameters * Fix trailing whitespace in DragAndDropImportTest * Don't commit LLM comments as file * FIX add api validation --------- Co-authored-by: Carlos Adames <cj@Carloss-MacBook-Air.local> Co-authored-by: Juan José Mata <jjmata@jjmata.com> Co-authored-by: sokie <sokysrm@gmail.com>	2026-01-10 16:39:18 +01:00