@arbidocs/client 0.3.47 → 0.3.49

package/dist/index.d.cts

@@ -2350,7 +2350,7 @@ interface components {
              * @default {
              *       "API_TYPE": "remote",
              *       "ENABLE_THINKING": true,
-             *       "MODEL_NAME": "GLM5@Fireworks",
+             *       "MODEL_NAME": "Premium",
              *       "SYSTEM_INSTRUCTION": "You are a code execution agent. You write and run code to accomplish tasks.\n\nYou have access to an execute_code tool that runs code in a sandboxed Docker container.\n\nThe sandbox has:\n- Python 3.12 with numpy, pandas, matplotlib, requests, beautifulsoup4,\n  httpx, pillow, sympy, pyyaml (plus uv for installing more)\n- Node.js 22 with TypeScript (ts-node) and npm\n- Bash with git, curl, wget, jq, sqlite3, build-essential\n- Network access (can pip/npm install additional packages)\n\nInstructions:\n1. Write clean, correct code to accomplish the user's task\n2. Always call execute_code to run your code — never guess the output\n3. If execution errors, analyze the traceback, fix the code, and retry\n4. Once you have the correct output, respond with ONLY the final result\n\nKeep code simple and direct. Prefer Python unless the task specifically requires another language.",
              *       "TEMPERATURE": 0.2,
              *       "MAX_TOKENS": 8000,
@@ -2386,7 +2386,7 @@ interface components {
              *       "MAX_NUMB_OF_CHUNKS": 30,
              *       "MAX_CONCURRENT_REQUESTS": 256,
              *       "MODEL_NAME": "Qwen/Qwen3-Reranker-0.6B",
-             *       "API_TYPE": "remote",
+             *       "API_TYPE": "local",
              *       "RETRIEVAL_INSTRUCTION": "Judge whether the passage contains the specific facts, figures, names, or references mentioned in the query. Only answer yes if the passage directly contains these details"
              *     }
              */
@@ -2400,15 +2400,14 @@ interface components {
             /**
              * @default {
              *       "MAX_CHUNK_TOKENS": 1200,
-             *       "TOKENIZER_TYPE": "huggingface",
-             *       "TOKENIZER_NAME": "Qwen/Qwen3-Embedding-0.6B"
+             *       "TOKENIZER_NAME": "cl100k_base"
              *     }
              */
             Chunker: components['schemas']['ChunkerConfig'];
             /**
              * @default {
              *       "MODEL_NAME": "Qwen/Qwen3-Embedding-0.6B",
-             *       "API_TYPE": "remote",
+             *       "API_TYPE": "local",
              *       "BATCH_SIZE": 128,
              *       "MAX_CONCURRENT_REQUESTS": 256,
              *       "DOCUMENT_PREFIX": "",
@@ -2762,21 +2761,14 @@ interface components {
         ChunkerConfig: {
             /**
              * Max Chunk Tokens
-             * @description Maximum tokens per chunk. The tokenizer used depends on TOKENIZER_TYPE.
+             * @description Maximum tokens per chunk. Enforces a hard upper bound on chunk size; the tiktoken encoding is model-agnostic and used only for counting.
              * @default 1200
              */
             MAX_CHUNK_TOKENS: number;
-            /**
-             * Tokenizer Type
-             * @description Tokenizer backend: 'tiktoken' for OpenAI models (cl100k_base, etc.) or 'huggingface' for HF models (Qwen3-Embedding, etc.).
-             * @default huggingface
-             * @enum {string}
-             */
-            TOKENIZER_TYPE: 'tiktoken' | 'huggingface';
             /**
              * Tokenizer Name
-             * @description Tokenizer name. For tiktoken: 'cl100k_base', 'o200k_base', etc. For huggingface: model name like 'Qwen/Qwen3-Embedding-0.6B'.
-             * @default Qwen/Qwen3-Embedding-0.6B
+             * @description Name of the tiktoken encoding used for chunk-size counting (e.g. 'cl100k_base', 'o200k_base').
+             * @default cl100k_base
              */
             TOKENIZER_NAME: string;
         };
@@ -2820,7 +2812,7 @@ interface components {
             /**
              * Model Name
              * @description Model for code generation. Should be a strong coding model.
-             * @default GLM5@Fireworks
+             * @default Premium
              */
             MODEL_NAME: string;
             /**
@@ -3410,8 +3402,8 @@ interface components {
          * @description A pair of documents identified as near-duplicates by centroid similarity.
          */
         DocSimPair: {
-            doc_a: components['schemas']['DocResponse'];
-            doc_b: components['schemas']['DocResponse'];
+            doc_a: components['schemas']['DocSimSummary'];
+            doc_b: components['schemas']['DocSimSummary'];
             /** Similarity */
             similarity: number;
         };
@@ -3425,6 +3417,16 @@ interface components {
             /** Pairs */
             pairs: components['schemas']['DocSimPair'][];
         };
+        /**
+         * DocSimSummary
+         * @description Lightweight document summary for the similar-documents endpoint.
+         */
+        DocSimSummary: {
+            /** External Id */
+            external_id: string;
+            /** File Name */
+            file_name?: string | null;
+        };
         /**
          * DocTagResponse
          * @description Response for doctag operations - the link between a document and a tag.
@@ -3466,7 +3468,7 @@ interface components {
             shared?: boolean | null;
             doc_metadata?: components['schemas']['DocMetadata'] | null;
             /** Status */
-            status?: 'processing' | null;
+            status?: ('processing' | 'reindex-sparse') | null;
             /** Content */
             content?: string | null;
             /**
@@ -3589,7 +3591,7 @@ interface components {
             /**
              * Api Type
              * @description The inference type (local or remote).
-             * @default remote
+             * @default local
              * @enum {string}
              */
             API_TYPE: 'local' | 'remote';
@@ -3940,7 +3942,7 @@ interface components {
              * @default uploading
              * @enum {string}
              */
-            status: 'uploading' | 'duplicate' | 'quota_exceeded' | 'unsupported' | 'empty';
+            status: 'uploading' | 'duplicate' | 'quota_exceeded' | 'unsupported' | 'empty' | 'low-content';
             /** Reason */
             reason?: string | null;
         };
@@ -5278,7 +5280,7 @@ interface components {
             /**
              * Api Type
              * @description The inference type (local or remote).
-             * @default remote
+             * @default local
              * @enum {string}
              */
             API_TYPE: 'local' | 'remote';
@@ -6570,7 +6572,7 @@ interface components {
              * Status
              * @enum {string}
              */
-            status: 'uploading' | 'queued' | 'parsing' | 'encrypting' | 'indexing' | 'analysing' | 'completed' | 'failed' | 'skipped' | 'empty';
+            status: 'uploading' | 'queued' | 'parsing' | 'encrypting' | 'indexing' | 'analysing' | 'completed' | 'failed' | 'skipped' | 'empty' | 'low-content';
             /** Progress */
             progress: number;
         };
@@ -7117,6 +7119,11 @@ interface components {
              * @default false
              */
             show_agent_sessions: boolean;
+            /**
+             * Use S3 Direct Upload
+             * @default false
+             */
+            use_s3_direct_upload: boolean;
             /**
              * Hide Online Status
              * @default false
@@ -7161,6 +7168,8 @@ interface components {
             show_pa_mode?: boolean | null;
             /** Show Agent Sessions */
             show_agent_sessions?: boolean | null;
+            /** Use S3 Direct Upload */
+            use_s3_direct_upload?: boolean | null;
             /** Hide Online Status */
             hide_online_status?: boolean | null;
             /** Muted Users */
@@ -8676,7 +8685,7 @@ interface operations {
     get_similar_documents: {
         parameters: {
             query?: {
-                /** @description Minimum similarity score (default 0.92 for near-duplicates) */
+                /** @description Minimum similarity score (default 0.95 for near-duplicates) */
                 threshold?: number;
                 /** @description Filter pairs involving a specific document */
                 doc_ext_id?: string | null;

package/dist/index.d.ts

@@ -2350,7 +2350,7 @@ interface components {
              * @default {
              *       "API_TYPE": "remote",
              *       "ENABLE_THINKING": true,
-             *       "MODEL_NAME": "GLM5@Fireworks",
+             *       "MODEL_NAME": "Premium",
              *       "SYSTEM_INSTRUCTION": "You are a code execution agent. You write and run code to accomplish tasks.\n\nYou have access to an execute_code tool that runs code in a sandboxed Docker container.\n\nThe sandbox has:\n- Python 3.12 with numpy, pandas, matplotlib, requests, beautifulsoup4,\n  httpx, pillow, sympy, pyyaml (plus uv for installing more)\n- Node.js 22 with TypeScript (ts-node) and npm\n- Bash with git, curl, wget, jq, sqlite3, build-essential\n- Network access (can pip/npm install additional packages)\n\nInstructions:\n1. Write clean, correct code to accomplish the user's task\n2. Always call execute_code to run your code — never guess the output\n3. If execution errors, analyze the traceback, fix the code, and retry\n4. Once you have the correct output, respond with ONLY the final result\n\nKeep code simple and direct. Prefer Python unless the task specifically requires another language.",
              *       "TEMPERATURE": 0.2,
              *       "MAX_TOKENS": 8000,
@@ -2386,7 +2386,7 @@ interface components {
              *       "MAX_NUMB_OF_CHUNKS": 30,
              *       "MAX_CONCURRENT_REQUESTS": 256,
              *       "MODEL_NAME": "Qwen/Qwen3-Reranker-0.6B",
-             *       "API_TYPE": "remote",
+             *       "API_TYPE": "local",
              *       "RETRIEVAL_INSTRUCTION": "Judge whether the passage contains the specific facts, figures, names, or references mentioned in the query. Only answer yes if the passage directly contains these details"
              *     }
              */
@@ -2400,15 +2400,14 @@ interface components {
             /**
              * @default {
              *       "MAX_CHUNK_TOKENS": 1200,
-             *       "TOKENIZER_TYPE": "huggingface",
-             *       "TOKENIZER_NAME": "Qwen/Qwen3-Embedding-0.6B"
+             *       "TOKENIZER_NAME": "cl100k_base"
              *     }
              */
             Chunker: components['schemas']['ChunkerConfig'];
             /**
              * @default {
              *       "MODEL_NAME": "Qwen/Qwen3-Embedding-0.6B",
-             *       "API_TYPE": "remote",
+             *       "API_TYPE": "local",
              *       "BATCH_SIZE": 128,
              *       "MAX_CONCURRENT_REQUESTS": 256,
              *       "DOCUMENT_PREFIX": "",
@@ -2762,21 +2761,14 @@ interface components {
         ChunkerConfig: {
             /**
              * Max Chunk Tokens
-             * @description Maximum tokens per chunk. The tokenizer used depends on TOKENIZER_TYPE.
+             * @description Maximum tokens per chunk. Enforces a hard upper bound on chunk size; the tiktoken encoding is model-agnostic and used only for counting.
              * @default 1200
              */
             MAX_CHUNK_TOKENS: number;
-            /**
-             * Tokenizer Type
-             * @description Tokenizer backend: 'tiktoken' for OpenAI models (cl100k_base, etc.) or 'huggingface' for HF models (Qwen3-Embedding, etc.).
-             * @default huggingface
-             * @enum {string}
-             */
-            TOKENIZER_TYPE: 'tiktoken' | 'huggingface';
             /**
              * Tokenizer Name
-             * @description Tokenizer name. For tiktoken: 'cl100k_base', 'o200k_base', etc. For huggingface: model name like 'Qwen/Qwen3-Embedding-0.6B'.
-             * @default Qwen/Qwen3-Embedding-0.6B
+             * @description Name of the tiktoken encoding used for chunk-size counting (e.g. 'cl100k_base', 'o200k_base').
+             * @default cl100k_base
              */
             TOKENIZER_NAME: string;
         };
@@ -2820,7 +2812,7 @@ interface components {
             /**
              * Model Name
              * @description Model for code generation. Should be a strong coding model.
-             * @default GLM5@Fireworks
+             * @default Premium
              */
             MODEL_NAME: string;
             /**
@@ -3410,8 +3402,8 @@ interface components {
          * @description A pair of documents identified as near-duplicates by centroid similarity.
          */
         DocSimPair: {
-            doc_a: components['schemas']['DocResponse'];
-            doc_b: components['schemas']['DocResponse'];
+            doc_a: components['schemas']['DocSimSummary'];
+            doc_b: components['schemas']['DocSimSummary'];
             /** Similarity */
             similarity: number;
         };
@@ -3425,6 +3417,16 @@ interface components {
             /** Pairs */
             pairs: components['schemas']['DocSimPair'][];
         };
+        /**
+         * DocSimSummary
+         * @description Lightweight document summary for the similar-documents endpoint.
+         */
+        DocSimSummary: {
+            /** External Id */
+            external_id: string;
+            /** File Name */
+            file_name?: string | null;
+        };
         /**
          * DocTagResponse
          * @description Response for doctag operations - the link between a document and a tag.
@@ -3466,7 +3468,7 @@ interface components {
             shared?: boolean | null;
             doc_metadata?: components['schemas']['DocMetadata'] | null;
             /** Status */
-            status?: 'processing' | null;
+            status?: ('processing' | 'reindex-sparse') | null;
             /** Content */
             content?: string | null;
             /**
@@ -3589,7 +3591,7 @@ interface components {
             /**
              * Api Type
              * @description The inference type (local or remote).
-             * @default remote
+             * @default local
              * @enum {string}
              */
             API_TYPE: 'local' | 'remote';
@@ -3940,7 +3942,7 @@ interface components {
              * @default uploading
              * @enum {string}
              */
-            status: 'uploading' | 'duplicate' | 'quota_exceeded' | 'unsupported' | 'empty';
+            status: 'uploading' | 'duplicate' | 'quota_exceeded' | 'unsupported' | 'empty' | 'low-content';
             /** Reason */
             reason?: string | null;
         };
@@ -5278,7 +5280,7 @@ interface components {
             /**
              * Api Type
              * @description The inference type (local or remote).
-             * @default remote
+             * @default local
              * @enum {string}
              */
             API_TYPE: 'local' | 'remote';
@@ -6570,7 +6572,7 @@ interface components {
              * Status
              * @enum {string}
              */
-            status: 'uploading' | 'queued' | 'parsing' | 'encrypting' | 'indexing' | 'analysing' | 'completed' | 'failed' | 'skipped' | 'empty';
+            status: 'uploading' | 'queued' | 'parsing' | 'encrypting' | 'indexing' | 'analysing' | 'completed' | 'failed' | 'skipped' | 'empty' | 'low-content';
             /** Progress */
             progress: number;
         };
@@ -7117,6 +7119,11 @@ interface components {
              * @default false
              */
             show_agent_sessions: boolean;
+            /**
+             * Use S3 Direct Upload
+             * @default false
+             */
+            use_s3_direct_upload: boolean;
             /**
              * Hide Online Status
              * @default false
@@ -7161,6 +7168,8 @@ interface components {
             show_pa_mode?: boolean | null;
             /** Show Agent Sessions */
             show_agent_sessions?: boolean | null;
+            /** Use S3 Direct Upload */
+            use_s3_direct_upload?: boolean | null;
             /** Hide Online Status */
             hide_online_status?: boolean | null;
             /** Muted Users */
@@ -8676,7 +8685,7 @@ interface operations {
     get_similar_documents: {
         parameters: {
             query?: {
-                /** @description Minimum similarity score (default 0.92 for near-duplicates) */
+                /** @description Minimum similarity score (default 0.95 for near-duplicates) */
                 threshold?: number;
                 /** @description Filter pairs involving a specific document */
                 doc_ext_id?: string | null;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@arbidocs/client",
-  "version": "0.3.47",
+  "version": "0.3.49",
   "description": "TypeScript SDK for the ARBI API — zero-knowledge auth, E2E encryption, and type-safe REST client",
   "type": "module",
   "main": "dist/index.cjs",