From c5078cc5f880df70c524d15f2c4bb5fd69235c06 Mon Sep 17 00:00:00 2001
From: NguyenND <ngodanguyen@gmail.com>
Date: Tue, 30 Jun 2026 11:45:22 -0400
Subject: [PATCH] Jun 30 - Add chat to AI analysis result (content from raw
 data)

---
 config.py            | 18 ++++++++++++++++++
 models.py            | 10 ++++++----
 routes/ai_summary.py | 24 +++++++++++++++++-------
 3 files changed, 41 insertions(+), 11 deletions(-)

diff --git a/config.py b/config.py
index 2bc299f..8dc29c3 100644
--- a/config.py
+++ b/config.py
@@ -409,6 +409,24 @@ def initialize_database():
             conn.commit()
             logger.info("Migration: added idx_activity_log_time index to activity_log.")
 
+        # ── ai_analysis_log: add document_text column if missing ──────────────
+        cursor.execute(
+            """
+            SELECT COUNT(*) FROM information_schema.COLUMNS
+            WHERE TABLE_SCHEMA = DATABASE()
+              AND TABLE_NAME   = 'ai_analysis_log'
+              AND COLUMN_NAME  = 'document_text'
+            """
+        )
+        (has_doc_text,) = cursor.fetchone()
+        if not has_doc_text:
+            cursor.execute(
+                "ALTER TABLE ai_analysis_log "
+                "ADD COLUMN document_text MEDIUMTEXT NULL AFTER criteria_snapshot"
+            )
+            conn.commit()
+            logger.info("Migration: added document_text column to ai_analysis_log.")
+
         # ── Seed app_settings from environment variables (first-run bootstrap) ─
         # Uses INSERT IGNORE so values already saved via the Admin UI are never
         # overwritten — .env only fills in keys that are completely absent.
diff --git a/models.py b/models.py
index ed1a524..eb1e6d5 100644
--- a/models.py
+++ b/models.py
@@ -1367,15 +1367,17 @@ def delete_criterion(admin_id: int, criterion_id: int):
 
 
 def save_ai_analysis(user_id: int, file_names: str, model: str,
-                     verdict, criteria_snapshot, summary_text: str) -> int:
+                     verdict, criteria_snapshot, summary_text: str,
+                     document_text: str = None) -> int:
     conn = None
     try:
         conn = get_connection()
         cur = conn.cursor()
         cur.execute(
-            "INSERT INTO ai_analysis_log (user_id, file_names, model, verdict, criteria_snapshot, summary_text) "
-            "VALUES (%s,%s,%s,%s,%s,%s)",
-            (user_id, file_names, model, verdict, criteria_snapshot, summary_text),
+            "INSERT INTO ai_analysis_log "
+            "(user_id, file_names, model, verdict, criteria_snapshot, document_text, summary_text) "
+            "VALUES (%s,%s,%s,%s,%s,%s,%s)",
+            (user_id, file_names, model, verdict, criteria_snapshot, document_text, summary_text),
         )
         conn.commit()
         new_id = cur.lastrowid
diff --git a/routes/ai_summary.py b/routes/ai_summary.py
index d9f73ef..71cee5e 100644
--- a/routes/ai_summary.py
+++ b/routes/ai_summary.py
@@ -100,7 +100,8 @@ def analyze():
     ])
     analysis_id = save_ai_analysis(
         user["id"], ", ".join(file_names), model,
-        result.get("verdict"), criteria_snap, result.get("summary", "")
+        result.get("verdict"), criteria_snap, result.get("summary", ""),
+        document_text=combined,
     )
     log_action(user["id"], "AI_ANALYSIS", "ai_analysis_log", analysis_id,
                f"AI analysis on {len(file_names)} file(s). Verdict: {result.get('verdict')}.")
@@ -472,15 +473,24 @@ def chat():
     if not api_key:
         return jsonify({"error": "Groq API key is not configured."}), 400
 
-    model   = get_setting("groq.model", GROQ_MODELS[0])
-    summary = (record.get("summary_text") or "")[:8000]
+    model = get_setting("groq.model", GROQ_MODELS[0])
+
+    # Prefer raw document text so the AI can answer questions from source material.
+    # Fall back to the stored summary for analyses run before this feature was added.
+    raw_text = (record.get("document_text") or "").strip()
+    if raw_text:
+        context_label = "ORIGINAL DOCUMENT CONTENT"
+        context_body  = raw_text[:12000]
+    else:
+        context_label = "ANALYZED DOCUMENT SUMMARY"
+        context_body  = (record.get("summary_text") or "")[:8000]
 
     system_msg = (
         "You are a government procurement analyst assistant. "
-        "The user has questions about a solicitation document that has already been analyzed. "
-        "Answer questions based solely on the analysis summary below. "
-        "If the information is not in the summary, say so clearly. Be concise and direct.\n\n"
-        "## ANALYZED DOCUMENT SUMMARY\n\n" + summary
+        "The user has questions about a solicitation document. "
+        "Answer based solely on the document content provided below. "
+        "If the information is not present, say so clearly. Be concise and direct.\n\n"
+        f"## {context_label}\n\n" + context_body
     )
 
     # Sanitize and cap conversation history at 20 turns