database_config_260214.json 5.9 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157
  1. {
  2. "version": 0,
  3. "ui": {
  4. "enable_signup": false
  5. },
  6. "rag": {
  7. "template": "### Task:\nRespond to the user query using the provided context, incorporating inline citations in the format [id] **only when the <source> tag includes an explicit id attribute** (e.g., <source id=\"1\">).\n\n### Guidelines:\n- If you don't know the answer, clearly state that.\n- If uncertain, ask the user for clarification.\n- Respond in the same language as the user's query.\n- If the context is unreadable or of poor quality, inform the user and provide the best possible answer.\n- 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.\n- **Only include inline citations using [id] (e.g., [1], [2]) when the <source> tag includes an id attribute.**\n- Do not cite if the <source> tag does not contain an id attribute.\n- Do not use XML tags in your response.\n- Ensure citations are concise and directly related to the information provided.\n\n### Example of Citation:\nIf the user asks about a specific topic and the information is found in a source with a provided id attribute, the response should include the citation like in the following example:\n* \"According to the study, the proposed method increases efficiency by 20% [1].\"\n\n### Output:\nProvide a clear and direct response to the user's query, including inline citations in the format [id] only when the <source> tag with id attribute is present in the context.\n\n<context>\n{{CONTEXT}}\n</context>\n",
  8. "top_k": 10,
  9. "bypass_embedding_and_retrieval": false,
  10. "full_context": false,
  11. "enable_hybrid_search": false,
  12. "enable_hybrid_search_enriched_texts": false,
  13. "top_k_reranker": 3,
  14. "relevance_threshold": 0,
  15. "hybrid_bm25_weight": 0.5,
  16. "CONTENT_EXTRACTION_ENGINE": "",
  17. "pdf_extract_images": false,
  18. "datalab_marker_api_key": "",
  19. "datalab_marker_api_base_url": "",
  20. "datalab_marker_additional_config": "",
  21. "datalab_marker_skip_cache": false,
  22. "datalab_marker_force_ocr": false,
  23. "datalab_marker_paginate": false,
  24. "datalab_marker_strip_existing_ocr": false,
  25. "datalab_marker_disable_image_extraction": false,
  26. "datalab_marker_format_lines": false,
  27. "datalab_marker_output_format": "markdown",
  28. "DATALAB_MARKER_USE_LLM": false,
  29. "external_document_loader_url": "",
  30. "external_document_loader_api_key": "",
  31. "tika_server_url": "http://tika:9998",
  32. "docling_server_url": "http://docling:5001",
  33. "docling_api_key": "",
  34. "docling_params": {},
  35. "document_intelligence_endpoint": "",
  36. "document_intelligence_key": "",
  37. "document_intelligence_model": "prebuilt-layout",
  38. "MISTRAL_OCR_API_BASE_URL": "https://api.mistral.ai/v1",
  39. "mistral_ocr_api_key": "",
  40. "mineru_api_mode": "local",
  41. "mineru_api_url": "http://localhost:8000",
  42. "mineru_api_key": "",
  43. "mineru_api_timeout": "300",
  44. "mineru_params": {},
  45. "reranking_engine": "",
  46. "external_reranker_url": "",
  47. "external_reranker_api_key": "",
  48. "external_reranker_timeout": "",
  49. "reranking_model": "jinaai/jina-reranker-v2-base-multilingual",
  50. "text_splitter": "",
  51. "chunk_size": 1200,
  52. "chunk_min_size_target": 300,
  53. "chunk_overlap": 200,
  54. "file": {
  55. "max_size": null,
  56. "max_count": null,
  57. "allowed_extensions": []
  58. },
  59. "web": {
  60. "search": {
  61. "enable": true,
  62. "engine": "perplexity_search",
  63. "trust_env": false,
  64. "result_count": 3,
  65. "concurrent_requests": 0,
  66. "domain": {
  67. "filter_list": []
  68. },
  69. "bypass_embedding_and_retrieval": false,
  70. "bypass_web_loader": false,
  71. "ollama_cloud_api_key": "",
  72. "searxng_query_url": "http://100.87.1.24:8888/search?q=<query>&format=json&categories=general,news,science",
  73. "searxng_language": "all",
  74. "yacy_query_url": "",
  75. "yacy_username": "",
  76. "yacy_password": "",
  77. "google_pse_api_key": "",
  78. "google_pse_engine_id": "",
  79. "brave_search_api_key": "",
  80. "kagi_search_api_key": "",
  81. "mojeek_search_api_key": "",
  82. "bocha_search_api_key": "",
  83. "serpstack_api_key": "",
  84. "serpstack_https": true,
  85. "serper_api_key": "",
  86. "serply_api_key": "",
  87. "ddgs_backend": "auto",
  88. "tavily_api_key": "",
  89. "searchapi_api_key": "",
  90. "searchapi_engine": "",
  91. "serpapi_api_key": "",
  92. "serpapi_engine": "",
  93. "jina_api_key": "",
  94. "jina_api_base_url": "",
  95. "bing_search_v7_endpoint": "https://api.bing.microsoft.com/v7.0/search",
  96. "bing_search_v7_subscription_key": "",
  97. "exa_api_key": "",
  98. "perplexity_api_key": "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",
  99. "perplexity_model": "sonar",
  100. "perplexity_search_context_usage": "medium",
  101. "perplexity_search_api_url": "https://api.perplexity.ai/search",
  102. "sougou_api_sid": "",
  103. "sougou_api_sk": "",
  104. "external_web_search_url": "",
  105. "external_web_search_api_key": "",
  106. "tavily_extract_depth": "basic",
  107. "yandex_web_search_url": "",
  108. "yandex_web_search_api_key": "",
  109. "yandex_web_search_config": ""
  110. },
  111. "loader": {
  112. "concurrent_requests": 10,
  113. "engine": "",
  114. "timeout": "",
  115. "ssl_verification": true,
  116. "playwright_ws_url": "",
  117. "playwright_timeout": 10000,
  118. "firecrawl_api_key": "",
  119. "firecrawl_api_url": "https://api.firecrawl.dev",
  120. "firecrawl_timeout": "",
  121. "external_web_loader_url": "",
  122. "external_web_loader_api_key": ""
  123. }
  124. },
  125. "youtube_loader_language": [
  126. "en"
  127. ],
  128. "youtube_loader_proxy_url": "",
  129. "embedding_engine": "ollama",
  130. "embedding_model": "nomic-embed-text",
  131. "embedding_batch_size": 4,
  132. "enable_async_embedding": false,
  133. "pdf_loader_mode": "page",
  134. "enable_markdown_header_text_splitter": true,
  135. "openai_api_base_url": "https://api.openai.com/v1",
  136. "openai_api_key": "",
  137. "ollama": {
  138. "url": "http://100.87.1.24:11434",
  139. "key": ""
  140. },
  141. "azure_openai": {
  142. "base_url": "",
  143. "api_key": "",
  144. "api_version": ""
  145. }
  146. },
  147. "file": {
  148. "image_compression_width": null,
  149. "image_compression_height": null
  150. },
  151. "google_drive": {
  152. "enable": false
  153. },
  154. "onedrive": {
  155. "enable": false
  156. }
  157. }