Cannot run benchmark #75
Description
I am trying to run the benchmark but I get errors, both for BEIR as for KILT but neither of them are working. I am using a freshly installed conda environment but there seems to be an incompatibility for elasticsearch:
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
elasticsearch-haystack 1.0.1 requires elasticsearch<9,>=8, but you have elasticsearch 7.9.1 which is incompatible.Here is the whole bash script I use with a copy of the error I get for each of the benchmark:
#!/bin/bash
# script to run fastrag
conda deactivate
conda remove -n rag ENV --all -y
filepath="/home/pelirrojito/rag/fastrag/fastRAG"
cd $filepath
conda create -n rag python=3.9 -y
conda activate rag
pip install . # fastrag
pip install fastrag[elastic]
pip install fastrag[colbert]
# pip install git+https://github.com/facebookresearch/KILT.git
pip install beir
echo -e "\n\nResults\n\n"
# BEIR
# python "$filepath/benchmarks/BEIR/nq-plaid.py" # installation succesfull but can't run the model because I don't understand the requirements for PLAIDDocumentStore
# During installation:
# elasticsearch-haystack 1.0.1 requires elasticsearch<9,>=8, but you have elasticsearch 7.9.1 which is incompatible.
# When trying to run the code:
"""
2024-11-14 09:08:48 - Loading dataset...
2024-11-14 09:08:48 - Loading Corpus...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2681468/2681468 [00:07<00:00, 356143.51it/s]
2024-11-14 09:08:56 - Loaded 2681468 TEST Documents.
2024-11-14 09:08:56 - Doc Example: {'text': \"In accounting, minority interest (or non-controlling interest) is the portion of a subsidiary corporation's stock that is not owned by the parent corporation. The magnitude of the minority interest in the subsidiary company is generally less than 50% of outstanding shares, or the corporation would generally cease to be a subsidiary of the parent.[1]\", 'title': 'Minority interest'}
2024-11-14 09:08:56 - Loading Queries...
2024-11-14 09:08:56 - Loaded 3452 TEST Queries.
2024-11-14 09:08:56 - Query Example: what is non controlling interest on balance sheet
2024-11-14 09:08:56 - Loading PLAID index...
Traceback (most recent call last):
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 94, in load_from_index
loaded_config, _ = cls.from_path(metadata_path)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 44, in from_path
with open(name) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/benchmarks/datasets/nq/metadata.json'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File \"/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/nq-plaid.py\", line 41, in <module>
document_store = PLAIDDocumentStore(
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/fastrag/stores/plaid.py\", line 113, in __init__
self._load_index()
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/fastrag/stores/plaid.py\", line 120, in _load_index
self.store = Searcher(
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/searcher.py\", line 33, in __init__
self.index_config = ColBERTConfig.load_from_index(self.index)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 97, in load_from_index
loaded_config, _ = cls.from_path(metadata_path)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 44, in from_path
with open(name) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/benchmarks/datasets/nq/plan.json'
"""
# python "$filepath/benchmarks/BEIR/msmarco-plaid.py" # Same as previous
# python "$filepath/benchmarks/BEIR/nq-bm25-sbert.py" # cannot import name ElasticsearchDocumentStore from haystack.document_stores
# During installation:
# elasticsearch-haystack 1.0.1 requires elasticsearch<9,>=8, but you have elasticsearch 7.9.1 which is incompatible.
# When trying to run the code:
"""
2024-11-14 09:08:48 - Loading dataset...
2024-11-14 09:08:48 - Loading Corpus...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2681468/2681468 [00:07<00:00, 356143.51it/s]
2024-11-14 09:08:56 - Loaded 2681468 TEST Documents.
2024-11-14 09:08:56 - Doc Example: {'text': \"In accounting, minority interest (or non-controlling interest) is the portion of a subsidiary corporation's stock that is not owned by the parent corporation. The magnitude of the minority interest in the subsidiary company is generally less than 50% of outstanding shares, or the corporation would generally cease to be a subsidiary of the parent.[1]\", 'title': 'Minority interest'}
2024-11-14 09:08:56 - Loading Queries...
2024-11-14 09:08:56 - Loaded 3452 TEST Queries.
2024-11-14 09:08:56 - Query Example: what is non controlling interest on balance sheet
2024-11-14 09:08:56 - Loading PLAID index...
Traceback (most recent call last):
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 94, in load_from_index
loaded_config, _ = cls.from_path(metadata_path)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 44, in from_path
with open(name) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/benchmarks/datasets/nq/metadata.json'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File \"/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/nq-plaid.py\", line 41, in <module>
document_store = PLAIDDocumentStore(
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/fastrag/stores/plaid.py\", line 113, in __init__
self._load_index()
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/fastrag/stores/plaid.py\", line 120, in _load_index
self.store = Searcher(
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/searcher.py\", line 33, in __init__
self.index_config = ColBERTConfig.load_from_index(self.index)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 97, in load_from_index
loaded_config, _ = cls.from_path(metadata_path)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 44, in from_path
with open(name) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/benchmarks/datasets/nq/plan.json'
: File name too long
Traceback (most recent call last):
File \"/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/nq-bm25-sbert.py\", line 10, in <module>
from haystack.document_stores import ElasticsearchDocumentStore
ImportError: cannot import name 'ElasticsearchDocumentStore' from 'haystack.document_stores' (/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/haystack/document_stores/__init__.py)
"""
python "$filepath/benchmarks/BEIR/msmarco-bm25-sbert.py" # cannot import name ElasticsearchDocumentStore from haystack.document_stores
# During installation:
# elasticsearch-haystack 1.0.1 requires elasticsearch<9,>=8, but you have elasticsearch 7.9.1 which is incompatible.
# When trying to run the code:
"""
2024-11-14 09:08:48 - Loading dataset...
2024-11-14 09:08:48 - Loading Corpus...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2681468/2681468 [00:07<00:00, 356143.51it/s]
2024-11-14 09:08:56 - Loaded 2681468 TEST Documents.
2024-11-14 09:08:56 - Doc Example: {'text': \"In accounting, minority interest (or non-controlling interest) is the portion of a subsidiary corporation's stock that is not owned by the parent corporation. The magnitude of the minority interest in the subsidiary company is generally less than 50% of outstanding shares, or the corporation would generally cease to be a subsidiary of the parent.[1]\", 'title': 'Minority interest'}
2024-11-14 09:08:56 - Loading Queries...
2024-11-14 09:08:56 - Loaded 3452 TEST Queries.
2024-11-14 09:08:56 - Query Example: what is non controlling interest on balance sheet
2024-11-14 09:08:56 - Loading PLAID index...
Traceback (most recent call last):
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 94, in load_from_index
loaded_config, _ = cls.from_path(metadata_path)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 44, in from_path
with open(name) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/benchmarks/datasets/nq/metadata.json'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File \"/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/nq-plaid.py\", line 41, in <module>
document_store = PLAIDDocumentStore(
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/fastrag/stores/plaid.py\", line 113, in __init__
self._load_index()
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/fastrag/stores/plaid.py\", line 120, in _load_index
self.store = Searcher(
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/searcher.py\", line 33, in __init__
self.index_config = ColBERTConfig.load_from_index(self.index)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 97, in load_from_index
loaded_config, _ = cls.from_path(metadata_path)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 44, in from_path
with open(name) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/benchmarks/datasets/nq/plan.json'
: File name too long
-bash:
2024-11-14 09:08:48 - Loading dataset...
2024-11-14 09:08:48 - Loading Corpus...
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2681468/2681468 [00:07<00:00, 356143.51it/s]
2024-11-14 09:08:56 - Loaded 2681468 TEST Documents.
2024-11-14 09:08:56 - Doc Example: {'text': \"In accounting, minority interest (or non-controlling interest) is the portion of a subsidiary corporation's stock that is not owned by the parent corporation. The magnitude of the minority interest in the subsidiary company is generally less than 50% of outstanding shares, or the corporation would generally cease to be a subsidiary of the parent.[1]\", 'title': 'Minority interest'}
2024-11-14 09:08:56 - Loading Queries...
2024-11-14 09:08:56 - Loaded 3452 TEST Queries.
2024-11-14 09:08:56 - Query Example: what is non controlling interest on balance sheet
2024-11-14 09:08:56 - Loading PLAID index...
Traceback (most recent call last):
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 94, in load_from_index
loaded_config, _ = cls.from_path(metadata_path)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 44, in from_path
with open(name) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/benchmarks/datasets/nq/metadata.json'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File \"/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/nq-plaid.py\", line 41, in <module>
document_store = PLAIDDocumentStore(
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/fastrag/stores/plaid.py\", line 113, in __init__
self._load_index()
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/fastrag/stores/plaid.py\", line 120, in _load_index
self.store = Searcher(
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/searcher.py\", line 33, in __init__
self.index_config = ColBERTConfig.load_from_index(self.index)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 97, in load_from_index
loaded_config, _ = cls.from_path(metadata_path)
File \"/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/colbert/infra/config/base_config.py\", line 44, in from_path
with open(name) as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/benchmarks/datasets/nq/plan.json'
: File name too long
Traceback (most recent call last):
File \"/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/nq-bm25-sbert.py\", line 10, in <module>
from haystack.document_stores import ElasticsearchDocumentStore
ImportError: cannot import name 'ElasticsearchDocumentStore' from 'haystack.document_stores' (/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/haystack/document_stores/__init__.py)
: File name too long
Traceback (most recent call last):
File \"/home/pelirrojito/rag/fastrag/fastRAG/benchmarks/BEIR/msmarco-bm25-sbert.py\", line 10, in <module>
from haystack.document_stores import ElasticsearchDocumentStore
ImportError: cannot import name 'ElasticsearchDocumentStore' from 'haystack.document_stores' (/home/pelirrojito/miniforge3/envs/rag/lib/python3.9/site-packages/haystack/document_stores/__init__.py)
"""