@botpress/api 0.50.1 → 0.50.2

package/src/gen/state.ts

@@ -10548,6 +10548,10 @@ export const state = {
                           "minimum": 50,
                           "maximum": 2000,
                           "description": "The minimum length a standalone paragraph should have. If a paragraph is shorter than this, it will be merged with the next immediate paragraph."
+                        },
+                        "smartCleanup": {
+                          "type": "boolean",
+                          "description": "(Team/Enterprise plan only, charged as AI Spend) Enabling this will use a lightweight/inexpensive LLM to clean up the extracted content of PDF files before indexing them to increase the quality of the stored vectors, as PDFs often store raw text in unusual ways which when extracted may result in formatting issues (e.g. broken sentences/paragraphs, unexpected headings, garbled characters, etc.) that can affect retrieval performance for certain user queries if left untouched.\n\nNotes:\n- This feature is only available in Team and Enterprise plans.\n- This feature is only available for PDF files. If the file isn't a PDF, this setting will be ignored and no AI Spend will be incurred.\n- We recommend using this feature for PDFs that have custom layouts or design. For simple text-based PDFs like documents and books, this feature is usually not necessary.\n- The smart cleanup takes some time to perform due to the LLM calls involved, so enabling it will increase the total time it takes to index the file.\n- We take steps to prevent the original text from being fundamentally changed but due to the nature of LLMs this could theoretically still happen so it's recommended to review the passages generated for the file after indexing to ensure the content is still accurate.\n- This feature is limited to the first 30 pages or 20 KB of text in the PDF file (whichever comes first). If the file has more content than these limits then the rest of the file will be indexed as-is without any cleanup. If you need to clean up the content of the entire file, consider splitting it into smaller files."
                         }
                       },
                       "additionalProperties": false
@@ -10580,7 +10584,7 @@ export const state = {
                         "enable": {
                           "default": false,
                           "type": "boolean",
-                          "description": "Create summaries for this file and index them as standalone vectors. Enabling this option will incur in AI Spend cost (charged to the workspace of the bot) to generate the summaries based on the amount of content in the file and the summarization model used. Please note that this feature is only available in Team/Enterprise plans."
+                          "description": "(Team/Enterprise plan only, charged as AI Spend) Create summaries for this file and index them as standalone vectors. Enabling this option will incur in AI Spend cost (charged to the workspace of the bot) to generate the summaries based on the amount of content in the file and the summarization model used.\n\nPlease note that this feature is only available in Team and Enterprise plans."
                         },
                         "modelType": {
                           "default": "balanced",
@@ -12427,7 +12431,7 @@ export const state = {
     "title": "Botpress API",
     "description": "API for Botpress Cloud",
     "server": "https://api.botpress.cloud",
-    "version": "0.50.1",
+    "version": "0.50.2",
     "prefix": "v1"
   },
   "errors": [