File size: 5,001 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 |
node_lines:
- 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: [ ko_kiwi ]
- 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: cohere_reranker
- module_type: rankgpt
- module_type: jina_reranker
- module_type: colbert_reranker
- module_type: sentence_transformer_reranker
- module_type: flag_embedding_reranker
- module_type: flag_embedding_llm_reranker
- module_type: time_reranker
- module_type: openvino_reranker
- module_type: voyageai_reranker
- module_type: mixedbreadai_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
prompt: |
์ฌ๋ฌ ๋ฌธ๋งฅ ์ ๋ณด๋ ๋ค์๊ณผ ๊ฐ์ต๋๋ค.\n
---------------------\n
{context_str}\n
---------------------\n
์ฌ์ ์ง์์ด ์๋ ์ฌ๋ฌ ์ ๋ณด๊ฐ ์ฃผ์ด์ก์ต๋๋ค,
์ง๋ฌธ์ ๋๋ตํ์ธ์.\n
์ง๋ฌธ: {query_str}\n
๋ต๋ณ:
- module_type: refine
llm: openai
model: gpt-4o-mini
prompt: |
์๋ ์ง๋ฌธ์ ๋ค์๊ณผ ๊ฐ์ต๋๋ค: {query_str}
๊ธฐ์กด ๋ต๋ณ์ ๋ค์๊ณผ ๊ฐ์ต๋๋ค: {existing_answer}
์๋์์ ๊ธฐ์กด ๋ต๋ณ์ ์ ์ ํ ์ ์๋ ๊ธฐํ๊ฐ ์์ต๋๋ค.
(ํ์ํ ๊ฒฝ์ฐ์๋ง) ์๋์ ๋ช ๊ฐ์ง ๋งฅ๋ฝ์ ์ถ๊ฐํ์ฌ ๊ธฐ์กด ๋ต๋ณ์ ์ ์ ํ ์ ์์ต๋๋ค.
------------
{context_msg}
------------
์๋ก์ด ๋ฌธ๋งฅ์ด ์ฃผ์ด์ง๋ฉด ๊ธฐ์กด ๋ต๋ณ์ ์์ ํ์ฌ ์ง๋ฌธ์ ๋ํ ๋ต๋ณ์ ์ ์ ํฉ๋๋ค.
๋งฅ๋ฝ์ด ์ธ๋ชจ ์๋ค๋ฉด, ๊ธฐ์กด ๋ต๋ณ์ ๊ทธ๋๋ก ๋ต๋ณํ์ธ์.
์ ์ ๋ ๋ต๋ณ:
- 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
speed_threshold: 10
generator_modules:
- module_type: llama_index_llm
llm: openai
model: [gpt-4o-mini]
modules:
- module_type: fstring
prompt: ["์ฃผ์ด์ง passage๋ง์ ์ด์ฉํ์ฌ question์ ๋ฐ๋ผ ๋ตํ์์ค passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
- module_type: long_context_reorder
prompt: ["์ฃผ์ด์ง passage๋ง์ ์ด์ฉํ์ฌ question์ ๋ฐ๋ผ ๋ตํ์์ค passage: {retrieved_contents} \n\n Question: {query} \n\n Answer:"]
- node_type: generator
strategy:
metrics:
- metric_name: bleu
- metric_name: meteor
- metric_name: rouge
- metric_name: sem_score
embedding_model: openai
speed_threshold: 10
modules:
- module_type: llama_index_llm
llm: [openai]
model: [gpt-4o-mini]
temperature: [0.5, 1.0]
|