more error handling

def ask_llm_chunk(chunk, questions):
chunk = chunk.astype(str)
try:
inputs = tokenizer(table=chunk, queries=questions, padding="max_length", truncation=True, return_tensors="pt")
except Exception as e:
st.write(f"An error occurred: {e}")
return ["Error occurred while tokenizing"] * len(questions)

# Check for token limit
if inputs["input_ids"].shape[1] > 512:
st.warning("Token limit exceeded for chunk")
return ["Token limit exceeded for chunk"] * len(questions)

outputs = model(**inputs)
predicted_answer_coordinates, predicted_aggregation_indices = tokenizer.convert_logits_to_predictions(
inputs,
outputs.logits.detach(),
outputs.logits_aggregation.detach()
)

st.write(f"Testing DataFrame iloc: {chunk.iloc[0, 8]}") # Debugging line

answers = []
for coordinates in predicted_answer_coordinates:
if len(coordinates) == 1:
try:
st.write(f"Trying to access row {coordinates[0][0]}, col {coordinates[0][1]}") # Debugging line
answers.append(chunk.iloc[coordinates[0]].values)
except Exception as e:
st.write(f"An error occurred: {e}")
else:
cell_values = []
for coordinate in coordinates:
try:
cell_values.append(chunk.iloc[coordinate].values)
except Exception as e:
st.write(f"An error occurred: {e}")
answers.append(", ".join(cell_values))
return answers

app.py

@@ -12,43 +12,43 @@ def ask_llm_chunk(chunk, questions):
     chunk = chunk.astype(str)
     try:
         inputs = tokenizer(table=chunk, queries=questions, padding="max_length", truncation=True, return_tensors="pt")
-        st.write(f"Token shape: {inputs['input_ids'].shape[1]}")  # Debugging line
-        
-        # Check for token limit
-        if inputs["input_ids"].shape[1] > 512:
-            st.warning("Token limit exceeded for chunk")
-            return ["Token limit exceeded for chunk"] * len(questions)
-        
-        outputs = model(**inputs)
-        predicted_answer_coordinates, predicted_aggregation_indices = tokenizer.convert_logits_to_predictions(
-            inputs,
-            outputs.logits.detach(),
-            outputs.logits_aggregation.detach()
-        )
-        
-        answers = []
-        for coordinates in predicted_answer_coordinates:
-            st.write(f"Type of coordinates[0]: {type(coordinates[0])}")  # Debugging line
-            st.write(f"Value of coordinates[0]: {coordinates[0]}")  # Debugging line
-            
-            st.write(f"DataFrame shape: {chunk.shape}")  # Debugging line
-            
-            if len(coordinates) == 1:
-                row, col = coordinates[0]
-                st.write(f"Trying to access row {row}, col {col}")  # Debugging line
-                answers.append(chunk.iloc[row, col])
-            else:
-                cell_values = []
-                for coordinate in coordinates:
-                    row, col = coordinate
-                    st.write(f"Trying to access row {row}, col {col}")  # Debugging line
-                    cell_values.append(chunk.iloc[row, col])
-                answers.append(", ".join(map(str, cell_values)))
-        return answers
     except Exception as e:
         st.write(f"An error occurred: {e}")
         return ["Error occurred while tokenizing"] * len(questions)
 
+    # Check for token limit
+    if inputs["input_ids"].shape[1] > 512:
+        st.warning("Token limit exceeded for chunk")
+        return ["Token limit exceeded for chunk"] * len(questions)
+
+    outputs = model(**inputs)
+    predicted_answer_coordinates, predicted_aggregation_indices = tokenizer.convert_logits_to_predictions(
+        inputs,
+        outputs.logits.detach(),
+        outputs.logits_aggregation.detach()
+    )
+    
+    st.write(f"Testing DataFrame iloc: {chunk.iloc[0, 8]}")  # Debugging line
+    
+    answers = []
+    for coordinates in predicted_answer_coordinates:
+        if len(coordinates) == 1:
+            try:
+                st.write(f"Trying to access row {coordinates[0][0]}, col {coordinates[0][1]}")  # Debugging line
+                answers.append(chunk.iloc[coordinates[0]].values)
+            except Exception as e:
+                st.write(f"An error occurred: {e}")
+        else:
+            cell_values = []
+            for coordinate in coordinates:
+                try:
+                    cell_values.append(chunk.iloc[coordinate].values)
+                except Exception as e:
+                    st.write(f"An error occurred: {e}")
+            answers.append(", ".join(cell_values))
+    return answers
+
+