Hugging Face's logo

Spaces:
AutoRAG
/
RAG-Pipeline-Optimization
Running

App Files Community
RAG-Pipeline-Optimization
File size: 4,886 Bytes 
b8a3ef1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
 
node_lines:
- node_line_name: pre_retrieve_node_line  # Arbitrary node line name
  nodes:
    - node_type: query_expansion
      strategy:
        metrics: [retrieval_f1, retrieval_recall, retrieval_precision]
        speed_threshold: 10
        top_k: 10
        retrieval_modules:
          - module_type: bm25
            bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
          - module_type: vectordb
            embedding_model: openai
      modules:
        - module_type: pass_query_expansion
        - module_type: query_decompose
          generator_module_type: llama_index_llm
          llm: openai
          model: [ gpt-4o-mini ]
        - module_type: hyde
          generator_module_type: llama_index_llm
          llm: openai
          model: [ gpt-4o-mini ]
          max_token: 64
        - module_type: multi_query_expansion
          generator_module_type: llama_index_llm
          llm: openai
          temperature: [ 0.2, 1.0 ]
- node_line_name: retrieve_node_line  # Arbitrary node line name
  nodes:
    - node_type: retrieval
      strategy:
        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision,
                   retrieval_ndcg, retrieval_map, retrieval_mrr ]
        speed_threshold: 10
      top_k: 10
      modules:
        - module_type: bm25
          bm25_tokenizer: [ porter_stemmer, space, gpt2 ]
        - module_type: vectordb
          embedding_model: openai
          embedding_batch: 256
        - module_type: hybrid_rrf
          weight_range: (4,80)
        - module_type: hybrid_cc
          normalize_method: [ mm, tmm, z, dbsf ]
          weight_range: (0.0, 1.0)
          test_weight_size: 101
    - node_type: passage_augmenter
      strategy:
        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
        speed_threshold: 5
      top_k: 5
      embedding_model: openai
      modules:
        - module_type: pass_passage_augmenter
        - module_type: prev_next_augmenter
          mode: next
    - node_type: passage_reranker
      strategy:
        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
        speed_threshold: 10
      top_k: 5
      modules:
        - module_type: pass_reranker
        - module_type: tart
        - module_type: monot5
        - module_type: upr
        - module_type: rankgpt
        - module_type: colbert_reranker
        - module_type: sentence_transformer_reranker
        - module_type: flag_embedding_reranker
        - module_type: flag_embedding_llm_reranker
        - module_type: openvino_reranker
    - node_type: passage_filter
      strategy:
        metrics: [ retrieval_f1, retrieval_recall, retrieval_precision ]
        speed_threshold: 5
      modules:
        - module_type: pass_passage_filter
        - module_type: similarity_threshold_cutoff
          threshold: 0.85
        - module_type: similarity_percentile_cutoff
          percentile: 0.6
        - module_type: threshold_cutoff
          threshold: 0.85
        - module_type: percentile_cutoff
          percentile: 0.6
    - node_type: passage_compressor
      strategy:
        metrics: [retrieval_token_f1, retrieval_token_recall, retrieval_token_precision]
        speed_threshold: 10
      modules:
        - module_type: pass_compressor
        - module_type: tree_summarize
          llm: openai
          model: gpt-4o-mini
        - module_type: refine
          llm: openai
          model: gpt-4o-mini
        - module_type: longllmlingua
- node_line_name: post_retrieve_node_line  # Arbitrary node line name
  nodes:
    - node_type: prompt_maker
      strategy:
        metrics:
          - metric_name: bleu
          - metric_name: meteor
          - metric_name: rouge
          - metric_name: sem_score
            embedding_model: openai
          - metric_name: g_eval
        speed_threshold: 10
        generator_modules:
          - module_type: llama_index_llm
            llm: openai
            model: [gpt-4o-mini]
      modules:
        - module_type: fstring
          prompt: ["Tell me something about the question: {query} \n\n {retrieved_contents}",
                   "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?"]
        - module_type: long_context_reorder
          prompt: [ "Tell me something about the question: {query} \n\n {retrieved_contents}",
                    "Question: {query} \n Something to read: {retrieved_contents} \n What's your answer?" ]
    - node_type: generator
      strategy:
        metrics:
          - metric_name: bleu
          - metric_name: meteor
          - metric_name: rouge
          - metric_name: sem_score
            embedding_model: openai
          - metric_name: g_eval
        speed_threshold: 10
      modules:
        - module_type: llama_index_llm
          llm: [openai]
          model: [gpt-4o-mini]
          temperature: [0.5, 1.0]