Canner
部署成功，但是响应速度很慢，请问是什么问题？如何改进？
1.环境配置
Linux中部署，RTX 2080Ti(22GB) 22GB * 1，接入的是ollama，大模型是llama3:8b和nomic-embed-text:latest
2.问题
我只导入了一张表，然后在输入框问问题，但是响应速度很慢。请问是什么问题？如何改进？
你好，我和你电脑配置类似，你的config.yaml如何配置的是否可以展示。
type: llm provider: litellm_llm timeout: 1800 models:
- api_base: http://125.77.155.56:11434
model: ollama_chat/llama3:8b
alias: default
timeout: 1800
kwargs:
num_ctx: 2048
max_tokens: 4096 n: 1 temperature: 0 - model: gpt-4.1-mini-2025-04-14 context_window_size: 1000000 kwargs: max_tokens: 4096 n: 1 seed: 0 temperature: 0
- model: gpt-4.1-2025-04-14 context_window_size: 1000000 kwargs: max_tokens: 4096 n: 1 seed: 0 temperature: 0
- model: gpt-5-nano-2025-08-07 context_window_size: 380000 kwargs: max_completion_tokens: 4096 n: 1 seed: 0 reasoning_effort: minimal
- model: gpt-5-mini-2025-08-07 context_window_size: 380000 kwargs: max_completion_tokens: 4096 n: 1 seed: 0 reasoning_effort: minimal
- model: gpt-5-2025-08-07 context_window_size: 380000 kwargs: max_completion_tokens: 4096 n: 1 seed: 0 reasoning_effort: minimal
type: embedder provider: litellm_embedder models:
- model: ollama/nomic-embed-text:latest alias: default api_base: http://125.77.155.56:11434 timeout: 600
type: engine provider: wren_ui endpoint: http://wren-ui:3000
type: engine provider: wren_ibis endpoint: http://ibis-server:8000
type: document_store provider: qdrant location: http://qdrant:6333 embedding_model_dim: 768 timeout: 120 recreate_index: true
type: pipeline pipes:
- name: db_schema_indexing embedder: litellm_embedder.default document_store: qdrant
- name: historical_question_indexing embedder: litellm_embedder.default document_store: qdrant
- name: table_description_indexing embedder: litellm_embedder.default document_store: qdrant
- name: db_schema_retrieval llm: litellm_llm.default embedder: litellm_embedder.default document_store: qdrant
- name: historical_question_retrieval embedder: litellm_embedder.default document_store: qdrant
- name: sql_generation llm: litellm_llm.default engine: wren_ui document_store: qdrant
- name: sql_correction llm: litellm_llm.default engine: wren_ui document_store: qdrant
- name: followup_sql_generation llm: litellm_llm.default engine: wren_ui document_store: qdrant
- name: sql_answer llm: litellm_llm.default
- name: semantics_description llm: litellm_llm.default
- name: relationship_recommendation llm: litellm_llm.default
- name: question_recommendation llm: litellm_llm.default
- name: question_recommendation_sql_generation llm: litellm_llm.default engine: wren_ui document_store: qdrant
- name: intent_classification llm: litellm_llm.default embedder: litellm_embedder.default document_store: qdrant
- name: misleading_assistance llm: litellm_llm.default
- name: data_assistance llm: litellm_llm.default
- name: sql_pairs_indexing document_store: qdrant embedder: litellm_embedder.default
- name: sql_pairs_retrieval document_store: qdrant embedder: litellm_embedder.default llm: litellm_llm.default
- name: preprocess_sql_data llm: litellm_llm.default
- name: sql_executor engine: wren_ui
- name: chart_generation llm: litellm_llm.default
- name: chart_adjustment llm: litellm_llm.default
- name: user_guide_assistance llm: litellm_llm.default
- name: sql_question_generation llm: litellm_llm.default
- name: sql_generation_reasoning llm: litellm_llm.default
- name: followup_sql_generation_reasoning llm: litellm_llm.default
- name: sql_regeneration llm: litellm_llm.default engine: wren_ui
- name: instructions_indexing embedder: litellm_embedder.default document_store: qdrant
- name: instructions_retrieval embedder: litellm_embedder.default document_store: qdrant
- name: sql_functions_retrieval engine: wren_ibis document_store: qdrant
- name: project_meta_indexing document_store: qdrant
- name: sql_tables_extraction llm: litellm_llm.default
- name: question_recommendation_db_schema_retrieval llm: litellm_llm.default embedder: litellm_embedder.default document_store: qdrant
settings: doc_endpoint: https://docs.getwren.ai is_oss: true engine_timeout: 30 column_indexing_batch_size: 50 table_retrieval_size: 10 table_column_retrieval_size: 100 allow_intent_classification: true allow_sql_generation_reasoning: true allow_sql_functions_retrieval: true enable_column_pruning: false max_sql_correction_retries: 3 query_cache_maxsize: 1000 query_cache_ttl: 3600 langfuse_host: https://cloud.langfuse.com langfuse_enable: true logging_level: DEBUG development: false historical_question_retrieval_similarity_threshold: 0.9 sql_pairs_similarity_threshold: 0.7 sql_pairs_retrieval_max_size: 10 instructions_similarity_threshold: 0.7 instructions_top_k: 10
