explain this error : nodes_retrieved = retriever.retrieve(AttributeError: type object 'r

Please stand by @tatanfort as I search the knowledge base. I normally take about 20 seconds or so. :wave:

----------------------
The error message you're seeing, AttributeError: type object 'retriever' has no attribute 'retrieve', typically means that the object retriever does not have a method called retrieve.

In the context of LlamaIndex, a retriever should be an instance of a class that inherits from BaseRetriever or one of its subclasses. These classes do have a retrieve method. For example, in the CustomRetriever class () example, the retrieve method is defined as _retrieve.

Here's an example of how a retriever should be defined and used:

```python
from llama_index import QueryBundle
from llama_index.schema import NodeWithScore
from llama_index.retrievers import BaseRetriever, VectorIndexRetriever, KeywordTableSimpleRetriever
from typing import List

class CustomRetriever(BaseRetriever):
"""Custom retriever that performs both semantic search and hybrid search."""

def init(
self,
vector_retriever: VectorIndexRetriever,
keyword_retriever: KeywordTableSimpleRetriever,
mode: str = "AND",
) -> None:
"""Init params."""

self._vector_retriever = vector_retriever
self._keyword_retriever = keyword_retriever
if mode not in ("AND", "OR"):
raise ValueError("Invalid mode.")
self._mode = mode
super().init()

def _retrieve(self, query_bundle: QueryBundle) -> List[NodeWithScore]:
"""Retrieve nodes given query."""

vector_nodes = self._vector_retriever.retrieve(query_bundle)
keyword_nodes = self._keyword_retriever.retrieve(query_bundle)

vector_ids = {n.node.node_id for n in vector_nodes}
keyword_ids = {n.node.node_id for n in keyword_nodes}

combined_dict = {n.node.node_id: n for n in vector_nodes}
combined_dict.update({n.node.node_id: n for n in keyword_nodes})

if self._mode == "AND":
retrieve_ids = vector_ids.intersection(keyword_ids)
else:
retrieve_ids = vector_ids.union(keyword_ids)

retrieve_nodes = [combined_dict[rid] for rid in retrieve_ids]
return retrieve_nodes

Create an instance of CustomRetriever

retriever = CustomRetriever(vector_retriever, keyword_retriever, mode="AND")

Now you can call the retrieve method

nodes_retrieved = retriever.retrieve(query_bundle)
`` Please ensure that your retriever object is an instance of a class that has a retrieve` method. If you're still having trouble, please refer to the LlamaIndex documentation () for more information.
----------------------
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
----------------------

How did you create the retriever? Pretty weird error