Printing the text in a failed llm_parse_json (#629)

paperqa/core.py

@@ -13,29 +13,25 @@
 def llm_parse_json(text: str) -> dict:
     """Read LLM output and extract JSON data from it."""
     # fetch from markdown ```json if present
-    text = text.strip().split("```json")[-1].split("```")[0]
-    # split anything before the first {
-    text = "{" + text.split("{", 1)[-1]
-    # split anything after the last }
-    text = text.rsplit("}", 1)[0] + "}"
+    ptext = text.strip().split("```json")[-1].split("```")[0]
+    # split anything before the first { after the last }
+    ptext = ("{" + ptext.split("{", 1)[-1]).rsplit("}", 1)[0] + "}"
 
-    # escape new lines within strings
-    def replace_newlines(match: re.Match) -> str:
+    def escape_newlines(match: re.Match) -> str:
         return match.group(0).replace("\n", "\\n")
 
     # Match anything between double quotes
     # including escaped quotes and other escaped characters.
     # https://regex101.com/r/VFcDmB/1
     pattern = r'"(?:[^"\\]|\\.)*"'
-    text = re.sub(pattern, replace_newlines, text)
+    ptext = re.sub(pattern, escape_newlines, ptext)
     try:
-        return json.loads(text)
+        return json.loads(ptext)
     except json.JSONDecodeError as e:
         raise ValueError(
-            "Failed to parse JSON. Your model may not "
-            "be capable of supporting JSON output. Try "
-            "a different model or with "
-            "`Settings(prompts={'use_json': False})`"
+            f"Failed to parse JSON from text {text!r}. Your model may not be capable of"
+            " supporting JSON output or our parsing technique could use some work. Try"
+            " a different model or specify `Settings(prompts={'use_json': False})`"
         ) from e