getting a bit further with the frontend and demoing the analysis to matti

preparedness/utils.py

@@ -21,4 +21,34 @@ def get_ollama_embedding(text, model="nomic-embed-text"):
     }
     response = requests.post(url, json=payload)
     response.raise_for_status()
-    return response.json()["embedding"]
+    return response.json()["embedding"]
+
+def parse_combined_text_to_dict(s: str) -> dict:
+    """Parse a string of the form 'key1: value1 | key2: value2' into a dict.
+
+    Rules:
+    - Split on ' | ' to get key:value segments.
+    - For each segment, split on the first ':' to separate key and value.
+    - Strip whitespace. If a value is 'nan' (case-insensitive) or empty, use None.
+    - Return a dict mapping keys to values or None.
+    """
+    if not s:
+        return {}
+    result = {}
+    parts = [p.strip() for p in s.split("|")]
+    for part in parts:
+        if not part:
+            continue
+        # split on the first colon
+        if ':' in part:
+            k, v = part.split(':', 1)
+            k = k.strip()
+            v = v.strip()
+            if v.lower() == 'nan' or v == '':
+                result[k] = None
+            else:
+                result[k] = v
+        else:
+            # fallback: store whole segment under a numeric key
+            result.setdefault('_extra', []).append(part)
+    return result