Initial Commit

projects/benchmark_sample/0/config.yaml

@@ -0,0 +1,92 @@
+vectordb:
+  - name: chroma_dragonkue2
+    db_type: chroma
+    client_type: persistent
+    embedding_model: huggingface_drangonku-v2-ko
+    collection_name: huggingface_drangonku-v2-ko
+    path: ${PROJECT_DIR}/resources/chroma
+
+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, ko_okt ]
+        - module_type: vectordb
+          vectordb: chroma_dragonkue2 # chromadb
+        - module_type: hybrid_cc
+          normalize_method: [ mm, tmm, z, dbsf ]
+          target_modules: ('bm25', 'vectordb')
+          weight_range: (0.6, 0.4)
+          test_weight_size: 101
+    - node_type: passage_reranker # re-ranker
+      strategy:
+        metrics:
+        - retrieval_recall
+        - retrieval_precision
+        - retrieval_map
+      modules:
+      - module_type: dragonkue2
+        top_k: 5
+
+- node_line_name: post_retrieve_node_line # 생성노드
+  nodes:
+  - node_type: prompt_maker
+    strategy:
+      metrics:
+      - metric_name: bleu
+      - metric_name: meteor
+      - metric_name: rouge
+      - metric_name: sem_score
+        embedding_model: huggingface_drangonku-v2-ko  # raise ValueError("Only one embedding model is supported")
+        lang: ko
+      generator_modules:
+      - module_type: llama_index_llm
+        llm: ollama
+        model: [ gemma3:12b, phi4, deepseek-r1:14b, aya-expanse:8b ]
+        request_timeout: 3000.0
+    modules:
+      - module_type: fstring
+        prompt:
+        - |
+          ### Task:
+          Respond to the user query using the provided context.
+
+          ### Guidelines:
+          - If you don't know the answer, clearly state that.
+          - If uncertain, ask the user for clarification.
+          - Respond in the same language as the user's query.
+          - If the context is unreadable or of poor quality, inform the user and provide the best possible answer.
+          - If the answer isn't present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding.
+          - Do not use XML tags in your response.
+
+          ### Output:
+          Provide a clear and direct response to the user's query.
+
+          <context>
+          {retrieved_contents}
+          </context>
+
+          <user_query>
+          {query}
+          </user_query>
+  - node_type: generator # Gen-LLM
+    strategy: 
+      metrics:
+      - metric_name: bleu
+      - metric_name: meteor
+      - metric_name: rouge
+      - metric_name: sem_score
+    modules:
+    - module_type: llama_index_llm
+      llm: ollama
+      model: gemma3:12b  # phi4, deepseek-r1:14b, aya-expanse:8b
+      temperature: 0.0 
+      request_timeout: 30000.0
+      batch: 4