Batch search in-memory without index results in TypeError if you pass document_metadatas

My code:

```python
def rag(args: SearchArgs) -> List[List[SearchResult]]:
RAG = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0", verbose=0)
metadata = [doc["metadata"] for doc in args["docs"]]
RAG.encode(
[doc["content"] for doc in args["docs"]],
document_metadatas=metadata,
)
k = args.get("k", 5)
search_results = RAG.search_encoded_docs(query=args["query"], k=k)
# ....
return search_results

res = rag(
{
"query": ["Hello World", "This is a test"],
"docs": [
{"content": "doc1", "metadata": {"id": 0}},
{"content": "doc2", "metadata": {"id": 1}},
],
}
)
```

Error:

```
Documents encoded!
Traceback (most recent call last):
File "/Users/james/Projects/TS/open-recommender/packages/cli/src/rag/rag.py", line 996, in
res = rag(
^^^^
File "/Users/james/Projects/TS/open-recommender/packages/cli/src/rag/rag.py", line 37, in rag
search_results = RAG.search_encoded_docs(query=args["query"], k=k)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/james/Projects/TS/open-recommender/env/lib/python3.11/site-packages/ragatouille/RAGPretrainedModel.py", line 377, in search_encoded_docs
return self.model.search_encoded_docs(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/james/Projects/TS/open-recommender/env/lib/python3.11/site-packages/ragatouille/models/colbert.py", line 722, in search_encoded_docs
result["result_index"]
~~~~~~^^^^^^^^^^^^^^^^
TypeError: list indices must be integers or slices, not str
```

One thing I found confusing, and which seems to be causing this error too, is that `search_encoded_docs` returns either `List[SearchResult]` or a nested `List[List[SearchResult]]` depending on the number of queries. Maybe it would be better to just always return `List[List[SearchResult]]` otherwise we have to implement conditional logic based on the number of queries we pass, which we might not know ahead of time?

The error does not happen if I only pass one query, or if I don't pass `document_metadatas`.

Workaround:

```python
def rag(args: SearchArgs) -> List[List[SearchResult]]:
RAG = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0", verbose=0)
metadatas = [doc["metadata"] for doc in args["docs"]]
RAG.encode(
[doc["content"] for doc in args["docs"]],
# document_metadatas=metadatas,
)
k = args.get("k", 5)
search_results = RAG.search_encoded_docs(query=args["query"], k=k)
if type(search_results[0]) is not list:
for result in search_results:
result["metadata"] = metadatas[result["result_index"]]
return [search_results]
else:
for batch in search_results:
for result in batch:
result["metadata"] = metadatas[result["result_index"]]
return search_results
```

Start by reproducing the two-query example with document_metadatas, then inspect search_encoded_docs in ragatouille/RAGPretrainedModel.py and ragatouille/models/colbert.py, where the traceback shows the failure. Confirm the behavior for both single and batched queries; done means batched searches with metadata no longer raise the TypeError and the returned result shape is consistent or clearly documented.

Written by the indexing model from the issue text.