This is a FlexRetriever created with the
FlexRAG library (version
0.3.0).
The
enwiki_2020_atlas retriever is a FlexRetriever that provides access to the English Wikipedia corpus from December 2020. It is designed for information retrieval tasks, allowing users to search and retrieve relevant documents based on their queries.
The corpus of this retriever was created by the
Atlas project and the index was built using the
FlexRAG library.
You can use this retriever for information retrieval tasks. Here is an example:
1from flexrag.retriever import LocalRetriever
2
3
4# Load the retriever from the HuggingFace Hub
5retriever = LocalRetriever.load_from_hub("FlexRAG/enwiki_2020_atlas")
6
7
8# You can retrieve relevant documents now
9results = retriever.search("Who is Bruce Wayne?")
1python -m flexrag.entrypoints.run_interactive \
2 assistant_type=modular \
3 modular_config.used_fields=[title,text] \
4 modular_config.retriever_type="FlexRAG/enwiki_2020_atlas" \
5 modular_config.response_type=original \
6 modular_config.generator_type=openai \
7 modular_config.openai_config.model_name='gpt-4o-mini' \
8 modular_config.openai_config.api_key=$OPENAI_KEY \
9 modular_config.do_sample=False
As the corpus is based on the
CC-BY-SA 3.0 license, the retriever is also licensed under the same license.
