diff --git a/backend/__pycache__/database.cpython-313.pyc b/backend/__pycache__/database.cpython-313.pyc index 5a00784..d261fb4 100644 Binary files a/backend/__pycache__/database.cpython-313.pyc and b/backend/__pycache__/database.cpython-313.pyc differ diff --git a/backend/__pycache__/llm_service.cpython-313.pyc b/backend/__pycache__/llm_service.cpython-313.pyc new file mode 100644 index 0000000..5b47019 Binary files /dev/null and b/backend/__pycache__/llm_service.cpython-313.pyc differ diff --git a/backend/__pycache__/main.cpython-313.pyc b/backend/__pycache__/main.cpython-313.pyc index c17dccd..f1383cd 100644 Binary files a/backend/__pycache__/main.cpython-313.pyc and b/backend/__pycache__/main.cpython-313.pyc differ diff --git a/backend/database.py b/backend/database.py index 1467745..bbd8d60 100644 --- a/backend/database.py +++ b/backend/database.py @@ -1,23 +1,15 @@ import os +import urllib.parse from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, Boolean, ForeignKey, LargeBinary from sqlalchemy.ext.declarative import declarative_base from sqlalchemy.orm import sessionmaker, relationship +from sqlalchemy.dialects.postgresql import JSONB +from sqlalchemy.sql import func from dotenv import load_dotenv # Load environment variables load_dotenv() -DB_USER = os.getenv("DB_USER") -DB_PASSWORD = os.getenv("DB_PASSWORD") -DB_HOST = os.getenv("DB_HOST") -DB_PORT = os.getenv("DB_PORT") -import urllib.parse - -# ... (imports) - -# Load environment variables -load_dotenv() - DB_USER = os.getenv("DB_USER") DB_PASSWORD = os.getenv("DB_PASSWORD") DB_HOST = os.getenv("DB_HOST") @@ -54,10 +46,33 @@ class Attachment(Base): email_id = Column(Integer, ForeignKey("emails.id")) filename = Column(String) content_type = Column(String) - file_content = Column(LargeBinary) # Storing content directly in DB as requested - + file_path = Column(String, nullable=True) # Path to file on disk + file_content = Column(LargeBinary, nullable=True) # Stored in DB (for small files) + email = relationship("Email", back_populates="attachments") +class Vendor(Base): + __tablename__ = "vendors" + + id = Column(Integer, primary_key=True, index=True) + name = Column(String, unique=True, index=True) + default_model = Column(String, default="text") # 'text' (Gemma) or 'vision' (Qwen) + created_at = Column(DateTime(timezone=True), server_default=func.now()) + + documents = relationship("Document", back_populates="vendor") + +class Document(Base): + __tablename__ = "documents" + + id = Column(Integer, primary_key=True, index=True) + vendor_id = Column(Integer, ForeignKey("vendors.id"), nullable=True) + filename = Column(String) + upload_date = Column(DateTime(timezone=True), server_default=func.now()) + status = Column(String, default="pending") # pending, verified + processed_data = Column(JSONB) # The final verified JSON + + vendor = relationship("Vendor", back_populates="documents") + def get_db(): db = SessionLocal() try: diff --git a/backend/llm_service.py b/backend/llm_service.py new file mode 100644 index 0000000..1fc2182 --- /dev/null +++ b/backend/llm_service.py @@ -0,0 +1,54 @@ +import ollama +import json +import base64 + +def extract_data(text: str = None, image_path: str = None, model_type: str = "text") -> dict: + """ + Extracts structured data using either Text (Gemma) or Vision (Qwen) models. + """ + + prompt = """ + You are an expert data extraction assistant. + Extract the following fields from the provided document and return them as a SINGLE VALID JSON OBJECT: + - invoice_number (string) + - date (string) + - vendor_name (string) + - total_amount (string) + - currency (string) + - line_items (list of objects with: description, quantity, unit_price, total) + + IMPORTANT: + - Return ONLY the JSON. No markdown formatting, no explanations. + - If a field is not found, use null. + """ + + messages = [{'role': 'user', 'content': prompt}] + model = 'gemma:2b' + + if model_type == 'vision': + if not image_path: + return {"error": "Image path required for vision mode"} + + # Qwen-VL handles images passed in the message + model = 'qwen2.5vl:7b' # Using the installed model ID + messages[0]['images'] = [image_path] + messages[0]['content'] = "Analyze this image. " + prompt + else: + # Text Mode + if not text: + return {"error": "Text required for text mode"} + messages[0]['content'] += f"\n\n---\n{text}\n---" + + try: + response = ollama.chat(model=model, messages=messages) + content = response['message']['content'] + + # Clean up markdown + content = content.replace("```json", "").replace("```", "").strip() + + return json.loads(content) + + except Exception as e: + print(f"LLM Extraction Error ({model_type}): {e}") + return {"error": str(e), "raw_output": content if 'content' in locals() else ""} + diff --git a/backend/main.py b/backend/main.py index 7bd917a..5ac7444 100644 --- a/backend/main.py +++ b/backend/main.py @@ -44,7 +44,7 @@ def extract_text_from_pdf(file_bytes: bytes) -> str: return "" # Internal modules -from database import get_db, Email +from database import get_db, Email, Vendor, Document from scheduler import start_scheduler, stop_scheduler from mail_service import fetch_and_store_emails @@ -87,7 +87,7 @@ class LoginResponse(BaseModel): class NERResponse(BaseModel): text: str - + file_path: str def extract_text_from_image(file_bytes: bytes) -> str: @@ -104,13 +104,41 @@ async def extract_text(file: UploadFile = File(...)): content = await file.read() filename = file.filename.lower() + # Save file for Vision mode + file_path = f"uploads/{file.filename}" + with open(file_path, "wb") as f: + f.write(content) + extracted_text = "" if filename.endswith(".pdf"): # Try text extraction first - extracted_text = extract_text_from_pdf(content) - - # If text is empty, it might be a scanned PDF. + with pdfplumber.open(io.BytesIO(content)) as pdf: + try: + text = "" + for page in pdf.pages: + page_text = page.extract_text(layout=True) + if page_text: + text += page_text + "\n" + if text.strip(): + extracted_text = text.strip() + except Exception: + pass + + if not extracted_text: + try: + # Fallback to pypdf + reader = PdfReader(io.BytesIO(content)) + text = "" + for page in reader.pages: + page_text = page.extract_text() + if page_text: + text += page_text + "\n" + extracted_text = text.strip() + except: + pass + + # If text is still empty, it might be a scanned PDF. if not extracted_text.strip(): try: images = convert_from_bytes(content) @@ -125,7 +153,35 @@ async def extract_text(file: UploadFile = File(...)): else: raise HTTPException(status_code=400, detail="Unsupported file type") - return NERResponse(text=extracted_text) + return NERResponse(text=extracted_text, file_path=file_path) + +# 3. AI Extraction Module +from llm_service import extract_data +from pdf2image import convert_from_path + +class AITextRequest(BaseModel): + text: Optional[str] = None + file_path: Optional[str] = None + model_type: str = "text" + +@app.post("/api/extract/ai") +def extract_ai_data(request: AITextRequest): + final_image_path = request.file_path + + if request.model_type == "vision" and request.file_path and request.file_path.endswith(".pdf"): + # Convert PDF first page to image + try: + images = convert_from_path(request.file_path) + if images: + # Save temp image + temp_img_path = request.file_path + ".jpg" + images[0].save(temp_img_path, "JPEG") + final_image_path = temp_img_path + except Exception as e: + print(f"Error converting PDF for vision: {e}") + + data = extract_data(text=request.text, image_path=final_image_path, model_type=request.model_type) + return data import zipfile import mimetypes @@ -255,3 +311,36 @@ def sync_emails(): @app.get("/") def read_root(): return {"message": "OCR Backend API is running"} + +class DocumentSaveRequest(BaseModel): + vendor_name: str + file_path: str + model_type: str + data: dict + +@app.post("/api/documents/save") +def save_document(request: DocumentSaveRequest, db: Session = Depends(get_db)): + # 1. Find or Create Vendor + vendor = db.query(Vendor).filter(Vendor.name == request.vendor_name).first() + if not vendor: + vendor = Vendor(name=request.vendor_name, default_model=request.model_type) + db.add(vendor) + db.commit() + db.refresh(vendor) + else: + # Update preference + vendor.default_model = request.model_type + db.commit() + + # 2. Save Document + filename = request.file_path.split('/')[-1] + doc = Document( + vendor_id=vendor.id, + filename=filename, + status="verified", + processed_data=request.data + ) + db.add(doc) + db.commit() + + return {"message": "Document saved and Vendor preference updated", "vendor_id": vendor.id} diff --git a/backend/requirements.txt b/backend/requirements.txt index 8c7160e..db6102a 100644 --- a/backend/requirements.txt +++ b/backend/requirements.txt @@ -10,3 +10,4 @@ imap-tools apscheduler python-dotenv pdfplumber +ollama diff --git a/backend/uploads/Invoice For Oct-Nov-2025.pdf b/backend/uploads/Invoice For Oct-Nov-2025.pdf new file mode 100644 index 0000000..66410b4 Binary files /dev/null and b/backend/uploads/Invoice For Oct-Nov-2025.pdf differ diff --git a/backend/uploads/Invoice For Oct-Nov-2025.pdf.jpg b/backend/uploads/Invoice For Oct-Nov-2025.pdf.jpg new file mode 100644 index 0000000..8c8a1c2 Binary files /dev/null and b/backend/uploads/Invoice For Oct-Nov-2025.pdf.jpg differ diff --git a/backend/uploads/Purchase-Order-Template-01-TemplateLab.pdf b/backend/uploads/Purchase-Order-Template-01-TemplateLab.pdf new file mode 100644 index 0000000..fa171b4 Binary files /dev/null and b/backend/uploads/Purchase-Order-Template-01-TemplateLab.pdf differ diff --git a/frontend/src/app/ocr.service.ts b/frontend/src/app/ocr.service.ts index 492efb5..3b8a6ca 100644 --- a/frontend/src/app/ocr.service.ts +++ b/frontend/src/app/ocr.service.ts @@ -15,4 +15,12 @@ export class OcrService { formData.append('file', file); return this.http.post(`${this.apiUrl}/extract`, formData); } + + extractWithAI(text: string, filePath: string | null, modelType: string): Observable { + return this.http.post(`http://localhost:8000/api/extract/ai`, { text, file_path: filePath, model_type: modelType }); + } + + saveDocument(data: any): Observable { + return this.http.post(`http://localhost:8000/api/documents/save`, data); + } } diff --git a/frontend/src/app/ocr/ocr.component.ts b/frontend/src/app/ocr/ocr.component.ts index c743cd9..a5b23fa 100644 --- a/frontend/src/app/ocr/ocr.component.ts +++ b/frontend/src/app/ocr/ocr.component.ts @@ -9,6 +9,11 @@ import { FileUploadModule } from 'primeng/fileupload'; import { ProgressBarModule } from 'primeng/progressbar'; import { InputTextareaModule } from 'primeng/inputtextarea'; import { ToastModule } from 'primeng/toast'; +import { ButtonModule } from 'primeng/button'; +import { TableModule } from 'primeng/table'; +import { CardModule } from 'primeng/card'; +import { RadioButtonModule } from 'primeng/radiobutton'; +import { InputTextModule } from 'primeng/inputtext'; @Component({ selector: 'app-ocr', @@ -19,16 +24,18 @@ import { ToastModule } from 'primeng/toast'; FileUploadModule, ProgressBarModule, InputTextareaModule, - ToastModule + ToastModule, + ButtonModule, + TableModule, + CardModule, + RadioButtonModule, + InputTextModule ], providers: [MessageService], template: `

OCR Extraction

- +
-
-

Extracted Text Result:

- +
+
+

Extracted Text Result:

+ + +
+
+ +
+ + +
+
+ + +
+
+ + + +
+
+ +
+
+

AI Analysis Result:

+ +
+ + +
+
+ + +
+
+ + +
+
+ + +
+
+ + +
+
+ + + + + + Description + Qty + Price + Total + + + + + + + + + + + {{item.description}} + + + + + + + + + + {{item.quantity}} + + + + + + + + + + {{item.unit_price}} + + + + + + + + + + {{item.total}} + + + + + + +
@@ -65,16 +177,27 @@ import { ToastModule } from 'primeng/toast'; export class OcrComponent { extractedText: string | null = null; loading: boolean = false; + + aiLoading: boolean = false; + saveLoading: boolean = false; + aiResult: any = null; + + // Hybrid AI Props + modelType: string = 'text'; + filePath: string | null = null; constructor(private ocrService: OcrService, private messageService: MessageService) {} onUpload(event: any) { this.loading = true; + this.aiResult = null; // Reset AI result on new upload + this.filePath = null; const file = event.files[0]; this.ocrService.extractText(file).subscribe({ next: (res) => { this.extractedText = res.text; + this.filePath = res.file_path; this.loading = false; this.messageService.add({severity:'success', summary:'Success', detail:'Text Extracted Successfully'}); }, @@ -88,5 +211,50 @@ export class OcrComponent { onClear() { this.extractedText = null; + this.aiResult = null; + this.filePath = null; + } + + processWithAI() { + if (!this.extractedText) return; + + this.aiLoading = true; + // Pass text, filePath, and modelType + this.ocrService.extractWithAI(this.extractedText, this.filePath, this.modelType).subscribe({ + next: (res) => { + this.aiResult = res; + this.aiLoading = false; + this.messageService.add({severity:'success', summary:'AI Processing Complete', detail:'Data Extracted'}); + }, + error: (err) => { + console.error(err); + this.aiLoading = false; + this.messageService.add({severity:'error', summary:'AI Error', detail:'Could not process with AI'}); + } + }); + } + + saveDocument() { + if (!this.aiResult || !this.filePath) return; + + this.saveLoading = true; + const payload = { + vendor_name: this.aiResult.vendor_name || 'Unknown Vendor', + file_path: this.filePath, + model_type: this.modelType, + data: this.aiResult + }; + + this.ocrService.saveDocument(payload).subscribe({ + next: (res) => { + this.saveLoading = false; + this.messageService.add({severity:'success', summary:'Saved & Verified', detail:'Document and rules saved'}); + }, + error: (err) => { + console.error(err); + this.saveLoading = false; + this.messageService.add({severity:'error', summary:'Save Error', detail:'Failed to save document'}); + } + }); } }