Merge branch 'main' of https://huggingface.co/spaces/DataEyond/Agentic-Service-Data-Eyond into dev_new

.vscode/launch.json

@@ -0,0 +1,25 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "DataEyond: FastAPI (debug)",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "uvicorn",
+            "args": [
+                "main:app",
+                "--host", "0.0.0.0",
+                "--port", "7860",
+                "--reload"
+            ],
+            "jinja": true,
+            "justMyCode": true,
+            "envFile": "${workspaceFolder}/.env",
+            "console": "integratedTerminal",
+            "cwd": "${workspaceFolder}"
+        }
+    ]
+}

README.md

@@ -11,6 +11,8 @@ short_description: AI Agent core service
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
+# Agentic Service Data Eyond
+
 How to run:
 `uv run --no-sync uvicorn main:app --host 0.0.0.0 --port 7860`
 

src/api/v1/chat.py

@@ -61,15 +61,30 @@ def _extract_sources(results: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
     seen = set()
     sources = []
     for result in results:
-        meta = result["metadata"]
-        key = (meta.get("document_id"), meta.get("page_label"))
-        if key not in seen:
-            seen.add(key)
-            sources.append({
-                "document_id": meta.get("document_id"),
-                "filename": meta.get("filename", "Unknown"),
-                "page_label": meta.get("page_label"),
-            })
+        if "document_id" in result["metadata"]["data"]:
+            meta = result["metadata"]
+            key = (meta.get("document_id"), meta.get("page_label"))
+            if key not in seen:
+                seen.add(key)
+                sources.append({
+                    "document_id": meta.get("data", {}).get("document_id"),
+                    "filename": meta.get("data", {}).get("filename", "Unknown"),
+                    "page_label": meta.get("data", {}).get("page_label", "Unknown"),
+                })
+        else:
+            meta = result["metadata"]
+            key = (meta.get("table_name"), meta.get("column_name"))
+            if key not in seen:
+                seen.add(key)
+                table_name = meta.get("data", {}).get("table_name")
+                user_id = meta.get("user_id")
+                sources.append({
+                    "document_id": f"{user_id}_{table_name}",
+                    "filename": meta.get("data", {}).get("table_name", "Unknown"),
+                    "page_label": meta.get("data", {}).get("column_name", "Unknown"),
+                })
+
+    logger.debug(f"Extracted sources: {sources}")
     return sources
 
 

src/config/agents/system_prompt.md

@@ -3,8 +3,7 @@ You are a helpful AI assistant with access to user's uploaded documents. Your ro
 1. Answer questions based on provided document context
 2. If no relevant information is found in documents, acknowledge this honestly
 3. Be concise and direct in your responses
-4. Cite source documents when providing information
-5. If user's question is unclear, ask for clarification
+4. If user's question is unclear, ask for clarification
 
 When document context is provided:
 - Use information from documents to answer accurately