Update app.py

app.py

@@ -1864,16 +1864,201 @@ REPORT_FIELDS = [
     ("Allowable Bearing (kPa)", "kPa"),
 ]
 
+# -------------------------------
+# Imports
+# -------------------------------
+import io, re, json, tempfile
+from datetime import datetime
+from typing import Dict, Any, Optional, List
+
+import streamlit as st
+from reportlab.platypus import (
+    SimpleDocTemplate, Paragraph, Spacer, PageBreak, Table, TableStyle, Image as RLImage
+)
+from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
+from reportlab.lib import colors
+from reportlab.lib.pagesizes import A4
+from reportlab.lib.units import mm
+
+# -------------------------------
+# PDF Builder
+# -------------------------------
+def build_full_geotech_pdf(
+    site: Dict[str, Any],
+    filename: str,
+    include_map_image: Optional[bytes] = None,
+    ext_refs: Optional[List[str]] = None
+):
+    """
+    Build a professional PDF report using site data + references.
+    """
+    styles = getSampleStyleSheet()
+    title_style = ParagraphStyle(
+        "title", parent=styles["Title"], fontSize=20, alignment=1,
+        textColor=colors.HexColor("#FF7A00")
+    )
+    h1 = ParagraphStyle(
+        "h1", parent=styles["Heading1"], fontSize=14,
+        textColor=colors.HexColor("#1F4E79"), spaceAfter=6
+    )
+    body = ParagraphStyle("body", parent=styles["BodyText"], fontSize=10.5, leading=13)
+    bullet = ParagraphStyle("bullet", parent=body, leftIndent=12, bulletIndent=6)
+
+    doc = SimpleDocTemplate(
+        filename, pagesize=A4,
+        leftMargin=18*mm, rightMargin=18*mm,
+        topMargin=18*mm, bottomMargin=18*mm
+    )
+    elems = []
+
+    # --- Title page ---
+    elems.append(Paragraph("GEOTECHNICAL INVESTIGATION REPORT", title_style))
+    elems.append(Spacer(1, 12))
+    company = site.get("Company Name", "Client / Company: Not provided")
+    contact = site.get("Company Contact", "")
+    elems.append(Paragraph(f"<b>{company}</b>", body))
+    if contact:
+        elems.append(Paragraph(contact, body))
+    elems.append(Spacer(1, 12))
+    elems.append(Paragraph(f"<b>Project:</b> {site.get('Project Name','-')}", body))
+    elems.append(Paragraph(f"<b>Site:</b> {site.get('Site Name','-')}", body))
+    elems.append(Paragraph(f"<b>Date:</b> {datetime.today().strftime('%Y-%m-%d')}", body))
+    elems.append(PageBreak())
+
+    # --- Table of contents ---
+    elems.append(Paragraph("TABLE OF CONTENTS", h1))
+    toc_items = [
+        "1.0 Introduction",
+        "2.0 Site description and geology",
+        "3.0 Field investigation & laboratory testing",
+        "4.0 Evaluation of geotechnical properties",
+        "5.0 Provisional site classification",
+        "6.0 Recommendations",
+        "7.0 LLM Analysis",
+        "8.0 Figures & Tables",
+        "9.0 Appendices & References"
+    ]
+    for i, t in enumerate(toc_items, start=1):
+        elems.append(Paragraph(f"{i}. {t}", body))
+    elems.append(PageBreak())
+
+    # --- Summary ---
+    elems.append(Paragraph("SUMMARY", h1))
+    summary_bullets = [
+        f"Site: {site.get('Site Name','-')}.",
+        f"General geology: {site.get('Soil Profile','Not provided')}.",
+        f"Key lab tests: {', '.join([r.get('sampleId','') for r in site.get('Laboratory Results',[])]) if site.get('Laboratory Results') else 'No lab results provided.'}",
+        f"Classification: USCS = {site.get('USCS','Not provided')}; AASHTO = {site.get('AASHTO','Not provided')}.",
+        "Primary recommendation: See Recommendations section."
+    ]
+    for s in summary_bullets:
+        elems.append(Paragraph(f"• {s}", bullet))
+    elems.append(PageBreak())
+
+    # --- Introduction ---
+    elems.append(Paragraph("1.0 INTRODUCTION", h1))
+    intro_text = site.get("Project Description", "Project description not provided.")
+    elems.append(Paragraph(intro_text, body))
+
+    # --- Site description & geology ---
+    elems.append(Paragraph("2.0 SITE DESCRIPTION AND GEOLOGY", h1))
+    site_geo = [
+        f"Topography: {site.get('Topography','Not provided')}",
+        f"Drainage: {site.get('Drainage','Not provided')}",
+        f"Current land use: {site.get('Current Land Use','Not provided')}",
+        f"Regional geology: {site.get('Regional Geology','Not provided')}"
+    ]
+    for t in site_geo:
+        elems.append(Paragraph(t, body))
+    elems.append(PageBreak())
+
+    # --- Field & lab testing ---
+    elems.append(Paragraph("3.0 FIELD INVESTIGATION & LABORATORY TESTING", h1))
+    if site.get("Field Investigation"):
+        for item in site["Field Investigation"]:
+            elems.append(Paragraph(f"<b>{item.get('id','Test')}</b> — depth {item.get('depth','-')}", body))
+            for layer in item.get("layers", []):
+                elems.append(Paragraph(f"- {layer.get('depth','')} : {layer.get('description','')}", body))
+    else:
+        elems.append(Paragraph("No field investigation data supplied.", body))
+
+    lab_rows = site.get("Laboratory Results", [])
+    if lab_rows:
+        elems.append(Spacer(1, 6))
+        elems.append(Paragraph("Laboratory Results", h1))
+        data = [["Sample ID","Material","LL","PI","Linear Shrinkage","%Clay","%Silt","%Sand","%Gravel","Expansiveness"]]
+        for r in lab_rows:
+            data.append([
+                r.get("sampleId","-"), r.get("material","-"),
+                str(r.get("liquidLimit","-")), str(r.get("plasticityIndex","-")),
+                str(r.get("linearShrinkage","-")), str(r.get("percentClay","-")),
+                str(r.get("percentSilt","-")), str(r.get("percentSand","-")),
+                str(r.get("percentGravel","-")), r.get("potentialExpansiveness","-")
+            ])
+        t = Table(data, repeatRows=1, colWidths=[40*mm,40*mm,18*mm,18*mm,22*mm,20*mm,20*mm,20*mm,20*mm,30*mm])
+        t.setStyle(TableStyle([
+            ('BACKGROUND',(0,0),(-1,0),colors.HexColor("#1F4E79")),
+            ('TEXTCOLOR',(0,0),(-1,0),colors.white),
+            ('GRID',(0,0),(-1,-1),0.4,colors.grey),
+            ('BOX',(0,0),(-1,-1),1,colors.HexColor("#FF7A00"))
+        ]))
+        elems.append(t)
+    elems.append(PageBreak())
+
+    # --- Evaluation & classification ---
+    elems.append(Paragraph("4.0 EVALUATION OF GEOTECHNICAL PROPERTIES", h1))
+    elems.append(Paragraph(site.get("Evaluation","Evaluation not provided."), body))
+    elems.append(Paragraph("5.0 PROVISIONAL SITE CLASSIFICATION", h1))
+    elems.append(Paragraph(site.get("Provisional Classification","Not provided."), body))
+    elems.append(Paragraph("6.0 RECOMMENDATIONS", h1))
+    elems.append(Paragraph(site.get("Recommendations","Not provided."), body))
+
+    # --- LLM Analysis ---
+    elems.append(Paragraph("7.0 LLM ANALYSIS (GeoMate)", h1))
+    llm_text = site.get("LLM_Report_Text", None)
+    if llm_text:
+        elems.append(Paragraph(llm_text.replace("\n","\n\n"), body))
+    else:
+        elems.append(Paragraph("No LLM analysis saved for this site.", body))
+
+    # --- Map snapshot ---
+    if include_map_image:
+        try:
+            tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
+            tmp.write(include_map_image)
+            tmp.flush()
+            elems.append(PageBreak())
+            elems.append(Paragraph("Map Snapshot", h1))
+            elems.append(RLImage(tmp.name, width=160*mm, height=90*mm))
+        except Exception:
+            pass
+
+    # --- References ---
+    elems.append(PageBreak())
+    elems.append(Paragraph("9.0 APPENDICES & REFERENCES", h1))
+    if ext_refs:
+        for r in ext_refs:
+            elems.append(Paragraph(f"- {r}", body))
+    else:
+        elems.append(Paragraph("- No external references provided.", body))
+
+    doc.build(elems)
+    return filename
+
+
+# -------------------------------
+# Reports Page
+# -------------------------------
 def reports_page():
     st.header("📑 Reports — Classification & Full Geotechnical")
     site = st.session_state["sites"][st.session_state["active_site"]]
 
+    # ---------------- Classification Report ----------------
     st.subheader("Classification-only report")
     if site.get("classifier_decision"):
         st.markdown("You have a saved classification for this site.")
         if st.button("Generate Classification PDF"):
             fname = f"classification_{site['Site Name'].replace(' ','_')}.pdf"
-            # simple PDF
             buffer = io.BytesIO()
             doc = SimpleDocTemplate(buffer, pagesize=A4)
             elems = []
@@ -1883,25 +2068,34 @@ def reports_page():
             elems.append(Spacer(1,6))
             elems.append(Paragraph("Classification result:", getSampleStyleSheet()['Heading2']))
             elems.append(Paragraph(site.get("classifier_decision","-"), getSampleStyleSheet()['BodyText']))
+
+            # Add FAISS citations if present in rag_history
+            if "rag_history" in st.session_state and site.get("Site ID") in st.session_state["rag_history"]:
+                refs = []
+                for h in st.session_state["rag_history"][site["Site ID"]]:
+                    if h["who"]=="bot" and "[ref:" in h["text"]:
+                        for m in re.findall(r"\[ref:([^\]]+)\]", h["text"]):
+                            refs.append(m)
+                if refs:
+                    elems.append(Spacer(1,12))
+                    elems.append(Paragraph("References:", getSampleStyleSheet()['Heading2']))
+                    for r in set(refs):
+                        elems.append(Paragraph(f"- {r}", getSampleStyleSheet()['Normal']))
+
             doc.build(elems)
             buffer.seek(0)
             st.download_button("Download Classification PDF", buffer, file_name=fname, mime="application/pdf")
     else:
         st.info("No classification saved for this site yet. Use the Classifier page.")
 
-    # --------- Dynamic form for quick report inputs + LLM analysis ----------
+    # ---------------- Quick Report Form ----------------
     st.markdown("### Quick report form (edit values and request LLM analysis)")
-    site = st.session_state["sites"][st.session_state["active_site"]]
-
-    # Build form-style table
     with st.form(key="report_quick_form"):
-        cols = st.columns([2,1,1])  # name, value, unit/notes
-        # header row visually
+        cols = st.columns([2,1,1])
         cols[0].markdown("**Parameter**")
         cols[1].markdown("**Value**")
         cols[2].markdown("**Unit / Notes**")
 
-        # build inputs dynamically from REPORT_FIELDS
         inputs = {}
         for (fld, unit) in REPORT_FIELDS:
             c1, c2, c3 = st.columns([2,1,1])
@@ -1917,10 +2111,9 @@ def reports_page():
                 site[fld] = val if val != "" else "Not provided"
             st.success("Saved quick report values to active site.")
 
-    # LLM analysis button
+    # ---------------- LLM Analysis ----------------
     st.markdown("#### LLM-powered analysis")
     if st.button("Ask GeoMate (generate analysis & recommendations)"):
-        # prepare context for the LLM from the site
         context = {
             "site_name": site.get("Site Name"),
             "project": site.get("Project Name"),
@@ -1938,58 +2131,45 @@ def reports_page():
             "options and 4) short design notes. Provide any numeric outputs in the format [[FIELD: value unit]].\n\n"
             f"Context: {json.dumps(context)}\n\nAnswer concisely and professionally."
         )
-        # NOTE: Assuming groq_generate is a function you have defined elsewhere
         # resp = groq_generate(prompt, model=st.session_state["llm_model"], max_tokens=600)
-        resp = "This is a placeholder response for demonstration." # Placeholder
-        
-        # display
+        resp = "This is a placeholder response with citations [ref:Soil_Manual_2020] [[Load Bearing Capacity: 180 kPa]]"
+
         st.markdown("**GeoMate analysis**")
         st.markdown(resp)
-        # try to extract numeric fields (same bracket format as elsewhere)
+
         matches = re.findall(r"\[\[([A-Za-z0-9 _/-]+):\s*([0-9.+-eE]+)\s*([A-Za-z%\/]*)\]\]", resp)
         for m in matches:
-            field = m[0].strip()
-            val = m[1].strip()
-            unit = m[2].strip()
-            # map likely field names:
+            field, val, unit = m[0].strip(), m[1].strip(), m[2].strip()
             if "bearing" in field.lower():
                 site["Load Bearing Capacity"] = f"{val} {unit}"
             elif "skin" in field.lower():
                 site["Skin Shear Strength"] = f"{val} {unit}"
             elif "compaction" in field.lower():
                 site["Relative Compaction"] = f"{val} {unit}"
-        # store the analysis text so it can be included in the PDF later
+
         site["LLM_Report_Text"] = resp
         st.success("LLM analysis saved to site under 'LLM_Report_Text'.")
 
+    # ---------------- Full Report Chatbot ----------------
     st.markdown("---")
     st.subheader("Full Geotechnical Report (chatbot will gather missing fields)")
     if st.button("Start Report Chatbot"):
         st.session_state["sites"][st.session_state["active_site"]]["report_convo_state"] = 0
         st.rerun()
 
-    # Conversational data collection
     state = site.get("report_convo_state", -1)
     if state >= 0:
         st.markdown("Chatbot will ask for missing fields. You can answer or type 'skip' to leave blank.")
-        # Show current known fields
-        st.write("Current key parameters (live):")
-        show_table = []
-        for f,_ in REPORT_FIELDS:
-            show_table.append((f, site.get(f, "Not provided")))
+        show_table = [(f, site.get(f, "Not provided")) for f,_ in REPORT_FIELDS]
         st.table(show_table)
-        
-        # continue conversation step-by-step
+
         if state < len(REPORT_FIELDS):
             field, unit = REPORT_FIELDS[state]
             ans = st.text_input(f"GeoMate — Please provide '{field}' ({unit})", key=f"report_in_{state}")
             c1, c2 = st.columns([1,1])
             with c1:
                 if st.button("Submit", key=f"report_submit_{state}"):
-                    if ans.strip().lower() in ("skip","don't know","dont know","na","n/a",""):
-                        site[field] = "Not provided"
-                    else:
-                        site[field] = ans.strip()
+                    site[field] = ans.strip() if ans.strip() not in ("skip","don't know","dont know","na","n/a","") else "Not provided"
                     site["report_convo_state"] = state + 1
                     st.rerun()
             with c2:
@@ -1999,20 +2179,25 @@ def reports_page():
                     st.rerun()
         else:
             st.success("All report questions asked. You can generate the full report now.")
-            if st.button("Generate Full Geotechnical Report PDF"):
-                # Prepare ext_refs
-                ext_ref_text = st.text_area("Optional: External references (one per line)", value="")
-                ext_refs = [r.strip() for r in ext_ref_text.splitlines() if r.strip()]
-                # Build PDF using reportlab builder
-                outname = f"Full_Geotech_Report_{site.get('Site Name','site')}.pdf"
-                # include map image bytes if available
-                mapimg = site.get("map_snapshot")
-                # NOTE: Assuming build_full_geotech_pdf is defined elsewhere
-                # build_full_geotech_pdf(site, outname, include_map_image=mapimg, ext_refs=ext_refs)
-                st.info("Placeholder for PDF generation.") # Placeholder
-                # with open(outname, "rb") as f:
-                #     st.download_button("Download Full Geotechnical Report", f, file_name=outname, mime="application/pdf")
+            ext_ref_text = st.text_area("Optional: External references (one per line)", value="")
+            ext_refs = [r.strip() for r in ext_ref_text.splitlines() if r.strip()]
+
+            faiss_refs = []
+            if "rag_history" in st.session_state and site.get("Site ID") in st.session_state["rag_history"]:
+                for h in st.session_state["rag_history"][site["Site ID"]]:
+                    if h["who"]=="bot" and "[ref:" in h["text"]:
+                        for m in re.findall(r"\[ref:([^\]]+)\]", h["text"]):
+                            faiss_refs.append(m)
+            all_refs = list(set(ext_refs + faiss_refs))
+
+            outname = f"Full_Geotech_Report_{site.get('Site Name','site')}.pdf"
+            mapimg = site.get("map_snapshot")
+
+            build_full_geotech_pdf(site, outname, include_map_image=mapimg, ext_refs=all_refs)
 
+            with open(outname, "rb") as f:
+                st.download_button("Download Full Geotechnical Report", f, file_name=outname, mime="application/pdf")
+                
 # 8) Page router
 if "page" not in st.session_state:
     st.session_state["page"] = "Home"