Update FlexRAG retriever

.gitattributes

@@ -33,3 +33,40 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+database.lance/data/00e586a9-d3d8-4699-9c4e-6a18fc64622f.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/01a8a6b1-76b9-452f-b70a-b7cbe0fb8c82.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/11201b00-03c9-4d59-a83a-40c710abbc43.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/11284ea9-4f48-401b-8dd5-4731e49fc51e.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/1c602eb0-81dd-48a9-b9b5-26d0c73e9ed0.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/3eb4966c-276f-4c46-910a-5ee94ffcdde6.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/4722311c-d707-4ed4-a9e0-4c9278aed0e2.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/4a0c0ce9-e9d6-49c5-9378-f6b8558b5348.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/4e355326-b1d1-4469-b38e-175492d9968f.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/51724822-47cc-4850-bd13-0ba7baec2b01.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/54e8518c-2658-4250-a8b9-a0ebd1eb73f5.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/580e8c15-4c8b-4d1f-885f-c7ba9d14e603.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/59cb7ffa-0811-4a26-a2e4-8d175deca72f.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/5f8ec6ae-c488-49f0-88ef-6364a65d6db6.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/735f2485-76b4-4db9-9c60-21b5754b1a4d.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/771fd67a-05dc-408b-9431-62d49858b9eb.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/78555b8a-c5f5-4dd2-9f97-e269a6abe100.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/7c705929-881e-434a-8506-9834b497a227.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/7e0e8e07-463c-4c96-94a8-62d958906762.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/809ac450-ec48-48d1-8842-e3778526359f.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/8b7343ba-4e58-49ed-869d-ed7435417617.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/8bb61af3-776b-4000-acec-2e526dd44b1f.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/92201af5-6471-456f-b583-e93c5efa7f83.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/96e92d16-e08d-4c25-9710-4ae11ee7be47.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/ab2c98ff-98d1-4db3-8031-31a010d3a6b3.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/b1c6f9f4-4cd6-409e-b6c3-d7f72cefa8a0.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/bdc818aa-6136-41c8-bfaa-bac1f8663198.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/c7b9a7e9-d9e8-4ccc-ad2c-f29286090575.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/c7e0d1c8-9264-49b0-86c5-83bc2260a718.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/cda60dc8-ee89-494f-8771-74ccbc40aad9.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/d01fc446-5dc7-46e3-8040-e7dbcb39bc4a.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/d3e7b9cc-caef-4567-817f-fd155eb74adb.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/e19a72a2-63bf-48fd-9a42-925a161f9a5e.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/e2324dc3-3551-4cd9-8177-967ae61a25e3.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/f1caabfc-5fed-47e8-8764-93848d103d8a.lance filter=lfs diff=lfs merge=lfs -text
+database.lance/data/fef36975-cbef-49a1-89ac-0f1a7ae603a2.lance filter=lfs diff=lfs merge=lfs -text
+index.faiss filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+language: en
+library_name: FlexRAG
+tags:
+- FlexRAG
+- retrieval
+- search
+- lexical
+- RAG
+---
+
+# FlexRAG Retriever
+
+This is a DenseRetriever created with the [`FlexRAG`](https://github.com/ictnlp/flexrag) library (version `0.1.8`).
+
+## Installation
+
+You can install the `FlexRAG` library with `pip`:
+
+```bash
+pip install flexrag
+```
+
+## Loading a `FlexRAG` retriever
+
+You can use this retriever for information retrieval tasks. Here is an example:
+
+```python
+from flexrag.retriever import LocalRetriever
+
+# Load the retriever from the HuggingFace Hub
+retriever = LocalRetriever.load_from_hub("FlexRAG/wiki2021_atlas_contriever")
+
+# You can retrieve now
+results = retriever.search("Who is Bruce Wayne?")
+```
+
+FlexRAG Related Links:
+* 📚[Documentation](https://flexrag.readthedocs.io/en/latest/)
+* 💻[GitHub Repository](https://github.com/ictnlp/flexrag)

cls.id

@@ -0,0 +1 @@
+DenseRetriever

config.yaml

@@ -0,0 +1,197 @@
+index_type: faiss
+annoy_config:
+  distance_function: IP
+  index_train_num: 1000000
+  log_interval: 10000
+  batch_size: 512
+  n_trees: -1
+  n_jobs: -1
+  search_k: -1
+  on_disk_build: false
+faiss_config:
+  distance_function: IP
+  index_train_num: 1000000
+  log_interval: 10000
+  batch_size: 512
+  index_type: auto
+  n_subquantizers: 8
+  n_bits: 8
+  n_list: 1000
+  factory_str: null
+  n_probe: 32
+  device_id: []
+  k_factor: 10
+  polysemous_ht: 0
+  efSearch: 100
+scann_config:
+  distance_function: IP
+  index_train_num: 1000000
+  log_interval: 10000
+  batch_size: 512
+  num_leaves: 2000
+  num_leaves_to_search: 500
+  num_neighbors: 10
+  anisotropic_quantization_threshold: 0.2
+  dimensions_per_block: 2
+  threads: 0
+log_interval: 100000
+top_k: 10
+batch_size: 512
+query_preprocess_pipeline:
+  processor_type: []
+  length_filter_config:
+    max_tokens: null
+    min_tokens: null
+    max_chars: null
+    min_chars: null
+    max_bytes: null
+    min_bytes: null
+    tokenizer_config:
+      tokenizer_type: moses
+      hf_tokenizer_path: null
+      tiktok_tokenizer_name: null
+      lang: null
+  token_normalize_config:
+    lang: en
+    penn: true
+    norm_quote_commas: true
+    norm_numbers: true
+    pre_replace_unicode_punct: false
+    post_remove_control_chars: false
+    perl_parity: false
+  truncate_config:
+    max_chars: null
+    max_bytes: null
+    max_tokens: null
+    tokenizer_config:
+      tokenizer_type: moses
+      hf_tokenizer_path: null
+      tiktok_tokenizer_name: null
+      lang: null
+database_path: /data/zhangzhuocheng/Lab/Python/LLM/datasets/RAG/wikipedia/wiki_2021/contriever
+query_encoder_config:
+  encoder_type: hf
+  cohere_config:
+    model: embed-multilingual-v3.0
+    input_type: search_document
+    base_url: null
+    api_key: ???
+    proxy: null
+  hf_config:
+    model_path: facebook/contriever-msmarco
+    tokenizer_path: null
+    trust_remote_code: false
+    device_id: []
+    load_dtype: auto
+    max_encode_length: 512
+    encode_method: mean
+    normalize: false
+    prompt: ''
+    task: ''
+  hf_clip_config:
+    model_path: ???
+    tokenizer_path: null
+    trust_remote_code: false
+    device_id: []
+    load_dtype: auto
+    max_encode_length: 512
+    normalize: false
+    convert_to_rgb: false
+  jina_config:
+    model: jina-embeddings-v3
+    base_url: https://api.jina.ai/v1/embeddings
+    api_key: ???
+    dimensions: 1024
+    task: null
+    proxy: null
+  ollama_config:
+    model_name: ???
+    base_url: ???
+    prompt: null
+    verbose: false
+    embedding_size: 768
+    allow_parallel: true
+  openai_config:
+    is_azure: false
+    model_name: ???
+    base_url: null
+    api_key: EMPTY
+    api_version: 2024-07-01-preview
+    verbose: false
+    proxy: null
+    dimension: null
+  sentence_transformer_config:
+    model_path: ???
+    device_id: []
+    trust_remote_code: false
+    task: null
+    prompt_name: null
+    prompt: null
+    prompt_dict: null
+    normalize: false
+    model_kwargs: {}
+passage_encoder_config:
+  encoder_type: hf
+  cohere_config:
+    model: embed-multilingual-v3.0
+    input_type: search_document
+    base_url: null
+    api_key: ???
+    proxy: null
+  hf_config:
+    model_path: facebook/contriever-msmarco
+    tokenizer_path: null
+    trust_remote_code: false
+    device_id: []
+    load_dtype: auto
+    max_encode_length: 512
+    encode_method: mean
+    normalize: false
+    prompt: ''
+    task: ''
+  hf_clip_config:
+    model_path: ???
+    tokenizer_path: null
+    trust_remote_code: false
+    device_id: []
+    load_dtype: auto
+    max_encode_length: 512
+    normalize: false
+    convert_to_rgb: false
+  jina_config:
+    model: jina-embeddings-v3
+    base_url: https://api.jina.ai/v1/embeddings
+    api_key: ???
+    dimensions: 1024
+    task: null
+    proxy: null
+  ollama_config:
+    model_name: ???
+    base_url: ???
+    prompt: null
+    verbose: false
+    embedding_size: 768
+    allow_parallel: true
+  openai_config:
+    is_azure: false
+    model_name: ???
+    base_url: null
+    api_key: EMPTY
+    api_version: 2024-07-01-preview
+    verbose: false
+    proxy: null
+    dimension: null
+  sentence_transformer_config:
+    model_path: ???
+    device_id: []
+    trust_remote_code: false
+    task: null
+    prompt_name: null
+    prompt: null
+    prompt_dict: null
+    normalize: false
+    model_kwargs: {}
+encode_fields:
+- title
+- section
+- text

database.lance/data/00e586a9-d3d8-4699-9c4e-6a18fc64622f.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b231d58f3382e87e92d51d5bac98260ea1bee1bab49074946d891663e9ac887
+size 634796558

database.lance/data/01a8a6b1-76b9-452f-b70a-b7cbe0fb8c82.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d137b9e759f1104f01c3cc1b4d183606f348fc12fec6e525406e652f65a21dd
+size 534889655

database.lance/data/11201b00-03c9-4d59-a83a-40c710abbc43.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768c0276beca8c8da080938374757fb6c07441ebddab6aedaa365e1ab05f4fd5
+size 640606353

database.lance/data/11284ea9-4f48-401b-8dd5-4731e49fc51e.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5319362c88f6d6dc42b2ac963899e378608da0bb7f596e96f3bfa330b5a403
+size 640307726

database.lance/data/1c602eb0-81dd-48a9-b9b5-26d0c73e9ed0.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc1b6c533347d57b633c3cff7eccaf7b0360a9c98270899549efefc504358e9
+size 642330834

database.lance/data/3eb4966c-276f-4c46-910a-5ee94ffcdde6.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21536ae821e9f19676f324f42e72c0a015241a1484ae5de23b9ab1c6e0210a96
+size 538561495

database.lance/data/4722311c-d707-4ed4-a9e0-4c9278aed0e2.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474781c804c03c887ffd32919afe6209143b138fd0fcf3299f46908662281a56
+size 640925907

database.lance/data/4a0c0ce9-e9d6-49c5-9378-f6b8558b5348.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0510ecd9bbe270916c549caf57e941012a1395125d7e6988f8832fb82d91eb07
+size 632865677

database.lance/data/4e355326-b1d1-4469-b38e-175492d9968f.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4a6546d5eba1300a31cbb2cf7e9b5b97310fa4af09a5834f674d369d10bb02
+size 641556396

database.lance/data/51724822-47cc-4850-bd13-0ba7baec2b01.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae465d4c48474d930e435db0f1674cf7d425eeae1c72b3a62acb2d2809aa2494
+size 637563790

database.lance/data/54e8518c-2658-4250-a8b9-a0ebd1eb73f5.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9891e68b544c77bab4b112d5700e79c061b67425eed6861d30af5648dea835da
+size 641052625

database.lance/data/580e8c15-4c8b-4d1f-885f-c7ba9d14e603.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18372bdc2954eed752723b86f47a03f0f0ae1b4eab200d7c2d19783752fd84c8
+size 644660722

database.lance/data/59cb7ffa-0811-4a26-a2e4-8d175deca72f.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a16ce81bf4619b56400269ca625b0fe9906451bccc94dbb81ab5e50b5bc584f
+size 641993875

database.lance/data/5f8ec6ae-c488-49f0-88ef-6364a65d6db6.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7fb201f91927d888691e64ce96e250f7cc394544ad23fd3f4914c57821b7602
+size 641114129

database.lance/data/735f2485-76b4-4db9-9c60-21b5754b1a4d.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b03e8048380b85467d6193cc6bc0957ee20edb18447c86b65aaa3e103981c0
+size 428867518

database.lance/data/771fd67a-05dc-408b-9431-62d49858b9eb.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9243c8b9530473af79542d3dd2c7f504abe3e320848b0267b5743261eb4f0a23
+size 639752146

database.lance/data/78555b8a-c5f5-4dd2-9f97-e269a6abe100.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e51ff752cf3a0b4850aa2bb5fa42da069271e6984aa988e21a255ad307f6b8
+size 636138031

database.lance/data/7c705929-881e-434a-8506-9834b497a227.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eebc754e8f6848860dffe77043ca3edbaebbf66c077e2db82683a9c94f1479c7
+size 640980564

database.lance/data/7e0e8e07-463c-4c96-94a8-62d958906762.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92589b3e04f44011a9b31ac04a7b6cf01a99287ad0d14af5acd6867b771093bd
+size 633205902

database.lance/data/809ac450-ec48-48d1-8842-e3778526359f.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfebfe2f0bb57a5ebe66365bcae07b98ed143a3505eb06e08d36501df5b5fec7
+size 638642130

database.lance/data/8b7343ba-4e58-49ed-869d-ed7435417617.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abee57fd514300364bc2aee7b2fb364ac0dab902e30fc9ad698fdd596bfc9874
+size 637285330

database.lance/data/8bb61af3-776b-4000-acec-2e526dd44b1f.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60da526c6f0e5323ee8db8289c73c656aad43fd17e6fe908edb1ac1c27a12ce8
+size 636941427

database.lance/data/92201af5-6471-456f-b583-e93c5efa7f83.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f6f4e620fd62e075734b142caa0abf069d238c1ae3358a55538a47455f3f07
+size 642662575

database.lance/data/96e92d16-e08d-4c25-9710-4ae11ee7be47.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410cd4645d22430202c3e36a30fe409d93ef82b60d2ddb2f3436b5eb5b41a2b2
+size 641125841

database.lance/data/ab2c98ff-98d1-4db3-8031-31a010d3a6b3.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1c18ef9b9e299470415041d9ed9ebf9d70f8b3b7ce7b4dee858f2f996f7231
+size 607345453

database.lance/data/b1c6f9f4-4cd6-409e-b6c3-d7f72cefa8a0.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c23c52c3ae6c5ed2123a9eea066eb322ed2f782d6374452b4a9818ac9d71cd98
+size 641176147

database.lance/data/bdc818aa-6136-41c8-bfaa-bac1f8663198.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703421a6fe0c9e34efe8a31b17ab0b93f0202346b25d72c2caade4ae4f11b9e9
+size 546368058

database.lance/data/c7b9a7e9-d9e8-4ccc-ad2c-f29286090575.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414ebf59351c7ade8330ccbac70c40af158dbca82bcc2f35b99032e1c72e4f13
+size 641432337

database.lance/data/c7e0d1c8-9264-49b0-86c5-83bc2260a718.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c7a5c38941b6d87f63a01f2efe968831730fd4cfade793173fd6afbfe037ae
+size 641465068

database.lance/data/cda60dc8-ee89-494f-8771-74ccbc40aad9.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59fddf7a4bb4ece7e5ce3742671a8d99fb04653f40449a0bc65a5bd43372ea28
+size 638493905

database.lance/data/d01fc446-5dc7-46e3-8040-e7dbcb39bc4a.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01b58a2f836cec86e13e28a1f2a07d7411cf98ba1b601978abddec12819e99f
+size 637016529

database.lance/data/d3e7b9cc-caef-4567-817f-fd155eb74adb.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d06fb4482932f7796b616c1f5e0e8fc217f3c7d3388c2ac034cc2b7acb857eb
+size 639305869

database.lance/data/e19a72a2-63bf-48fd-9a42-925a161f9a5e.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938a7be8177e93646ce3011d9cef3c2c30843bcebc0eb182fddebee6cd3de3fb
+size 639961872

database.lance/data/e2324dc3-3551-4cd9-8177-967ae61a25e3.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4391720466c9dd8f74d3f36c24e6dd148b14eda0e0eeb2175cc5832e95f1022
+size 639610769

database.lance/data/f1caabfc-5fed-47e8-8764-93848d103d8a.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6bf9cc81c5d67e53c8096eed2c2ae9538947e5168aa21ad93809d5cb699572a
+size 636642831

database.lance/data/fef36975-cbef-49a1-89ac-0f1a7ae603a2.lance

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63a101a5b09828e4a1c9ad2fc1ee46e145a72f9f70efac21f0c845580bc2c2b
+size 641372687

index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b976c4e403e8f66e9f53614a24878e1c9ae714f7a1d4c1691823eac147ef66
+size 7526298936