Error M2 Ex1

Course Q&A Retrieval Augmented Generation
,
1 
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[9], line 2
      1 # Output is a list of indices
----> 2 bm25_retrieve("What are the recent news about GDP?")

Cell In[8], line 27, in bm25_retrieve(query, top_k)
     23 print(tokenized_query)
     25 # Use the 'BM25_RETRIEVER' to retrieve documents and their scores based on the tokenized query
     26 # Retrieve the top 'k' documents
---> 27 results, scores = BM25_RETRIEVER.retrieve(tokenized_query, 3)
     29 # Extract the first element from 'results' to get the list of retrieved documents
     30 results = None

File /opt/conda/lib/python3.12/site-packages/bm25s/__init__.py:866, in BM25.retrieve(self, query_tokens, corpus, k, sorted, return_as, show_progress, leave_progress, n_threads, chunksize, backend_selection, weight_mask)
    864     else:
    865         index_flat = indices.flatten().tolist()
--> 866         results = [corpus[i] for i in index_flat]
    867         retrieved_docs = np.array(results).reshape(indices.shape)
    869 if return_as == "tuple":

TypeError: 'int' object is not subscriptable
2

BTW, is it possible to reload the ‘original’ template? I want to get rid of all my previous codes and re-do the exercise from scratch. Thanks.

3

I figured it out. All good now.

4

Hi, I have the same issue but I still do not understand what is the problem in these two simple lines of code.

Any useful hint?

Thank

5

Hi all, this is happening because the second expected argument for BM25_RETRIEVER.retrieve is not the k you need to pass. So you actually need to pass k = top_k instead of only top_k.

I hope that helps. Let me know if you still encounter issues.

Cheers,
Lucas

2 Likes