The Document Assistant API enables developers to integrate document-based assistant functionalities into their applications using AODocs.
The first step is to enable AIDA (AODocs Intelligent Document Assistant) in your tenant. The support team will provide you with the necessary information on how to get started.
The second step is to enable AIDA on libraries. You need to be an administrator of the
library to do this.
AIDA can answer questions only from those documents that are in an AIDA enabled
library.
We create a vector store index for these documents. This can take some time. The get
library API provides the status of the indexation and an estimate of the time
remaining.
The content of the index is automatically kept up-to-date near real time with the
content changes.
The third step is to ask questions based on the AODocs documents.
AIDA automatically filters the results based on the user's permissions.
Authentication: All API endpoints require a valid OAuth2 token in the Authorization header. Ensure the client ID of the OAuth2 token is whitelisted in AODocs.
version: 1.1.0 servers: - url: https://document-assistant.us.aodocs.app description: Production US - url: https://document-assistant.eu.aodocs.app description: Production EU security: [] paths: /assistant/api/v1/tenants/{tenant}/documents:checkConflicts: post: tags: - document_conflict summary: Check Document Conflicts description: >- Create an async document conflict-check job and publish the final result to the requested Pub/Sub topic. operationId: >- check_document_conflicts_assistant_api_v1_tenants__tenant__documents_checkConflicts_post parameters: - name: tenant in: path required: true schema: anyOf: - type: string - type: 'null' description: The domain of the customer examples: - example.com title: Tenant description: The domain of the customer requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DocumentConflictCheckRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ConflictCheckJobResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: [] components: schemas: DocumentConflictCheckRequest: properties: llm_provider: anyOf: - $ref: '#/components/schemas/LlmProvider' - type: 'null' description: >- The LLM provider to use. If not provided, the default provider will be used. llm_model_prefix: anyOf: - type: string - type: 'null' title: Llm Model Prefix description: >- The prefix of the LLM model name to use. If not provided, the default model will be used. examples: - gemini-2.5-pro - gemini-2.5-pro-preview-05-06 - gpt-4.1 document_id: type: string title: Document Id description: The document ID of the files target_library_id: type: string title: Target Library Id description: Library ID containing the target documents to compare against. target_document_class_id: type: string title: Target Document Class Id description: >- Document class ID containing the target documents to compare against. pubsub_topic: anyOf: - type: string - type: 'null' title: Pubsub Topic description: Pub/Sub topic that will receive the final job envelope. join_conditions: items: $ref: '#/components/schemas/JoinCondition' type: array minItems: 1 title: Join Conditions description: All join conditions must match for a target document to be included. rules: items: oneOf: - $ref: '#/components/schemas/MetadataConflictRule' - $ref: '#/components/schemas/LLMConflictRule' discriminator: propertyName: kind mapping: llm: $ref: '#/components/schemas/LLMConflictRule' metadata: $ref: '#/components/schemas/MetadataConflictRule' type: array minItems: 1 title: Rules description: Conflict rules to execute on each matched target document. type: object required: - document_id - target_library_id - target_document_class_id - join_conditions - rules title: DocumentConflictCheckRequest ConflictCheckJobResponse: properties: job_id: type: string title: Job Id description: Conflict-check job ID. status: $ref: '#/components/schemas/ConflictCheckStatus' description: Job status. document_id: type: string title: Document Id description: Base document ID. target_library_id: type: string title: Target Library Id description: Target library ID. target_document_class_id: type: string title: Target Document Class Id description: Target document class ID. matched_documents: type: integer title: Matched Documents description: Number of matched target documents. conflicted_documents: type: integer title: Conflicted Documents description: Number of matched target documents with conflicts. notification_status: $ref: '#/components/schemas/NotificationStatus' description: Pub/Sub notification state for the final job envelope. result: anyOf: - $ref: '#/components/schemas/ConflictCheckResult' - type: 'null' description: Final result when the job has completed. error: anyOf: - type: string - type: 'null' title: Error description: Failure reason when the job has failed. expire_at: type: string format: date-time title: Expire At description: Automatic cleanup timestamp for the stored job. type: object required: - job_id - status - document_id - target_library_id - target_document_class_id - matched_documents - conflicted_documents - notification_status - expire_at title: ConflictCheckJobResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError LlmProvider: type: string enum: - OpenAI - Google - Altirnao - MistralAI - Anthropic title: LlmProvider JoinCondition: properties: base_field_id: type: string title: Base Field Id description: Field ID on the base document side. target_field_id: type: string title: Target Field Id description: Field ID on the target document side. type: object required: - base_field_id - target_field_id title: JoinCondition MetadataConflictRule: properties: kind: type: string const: metadata title: Kind default: metadata rule_id: type: string title: Rule Id description: Stable rule ID supplied by the caller. display_name: anyOf: - type: string - type: 'null' title: Display Name description: Optional human-readable label for the rule. description: anyOf: - type: string - type: 'null' title: Description description: Optional human-readable description of the rule. base_field_id: type: string title: Base Field Id description: Field ID on the base document side for this rule. target_field_id: type: string title: Target Field Id description: Field ID on the target document side for this rule. type: object required: - rule_id - base_field_id - target_field_id title: MetadataConflictRule LLMConflictRule: properties: kind: type: string const: llm title: Kind default: llm rule_id: type: string maxLength: 100 title: Rule Id description: Stable rule ID supplied by the caller. display_name: anyOf: - type: string maxLength: 100 - type: 'null' title: Display Name description: Optional human-readable label for the rule. description: anyOf: - type: string maxLength: 500 - type: 'null' title: Description description: Optional human-readable description of the rule for callers. conflict_definition: type: string maxLength: 500 title: Conflict Definition description: >- What should be treated as a conflict for this rule, e.g. 'any difference in the numeric interest rate or product fees'. This is the primary guidance the LLM uses to detect conflicts for this rule. examples: anyOf: - items: type: string maxLength: 200 type: array maxItems: 5 - type: 'null' title: Examples description: Optional example conflict descriptions to steer the model. additional_instructions: anyOf: - type: string maxLength: 500 - type: 'null' title: Additional Instructions description: Optional free-form extra guidance for the conflict detection. type: object required: - rule_id - conflict_definition title: LLMConflictRule ConflictCheckStatus: type: string enum: - PENDING - RUNNING - COMPLETED - FAILED title: ConflictCheckStatus NotificationStatus: type: string enum: - PENDING - SENT - FAILED title: NotificationStatus ConflictCheckResult: properties: matched_documents: type: integer title: Matched Documents description: Number of matched target documents evaluated. conflicted_documents: type: integer title: Conflicted Documents description: Number of matched target documents with at least one conflict. returned_conflicted_documents: type: integer title: Returned Conflicted Documents description: >- Number of conflicted target documents included in this result payload. truncated: type: boolean title: Truncated description: >- Whether conflicted target documents were capped in the result payload. llm_truncated: anyOf: - type: boolean - type: 'null' title: Llm Truncated description: >- Whether some matched documents were not checked by the LLM because the per-job LLM comparison budget was exhausted. None when the request had no LLM rule. llm_compared_documents: anyOf: - type: integer - type: 'null' title: Llm Compared Documents description: >- Number of matched documents actually compared by the LLM. None when the request had no LLM rule. llm_skipped_documents: anyOf: - type: integer - type: 'null' title: Llm Skipped Documents description: >- Number of matched documents skipped by the LLM because the per-job LLM comparison budget was exhausted. None when the request had no LLM rule. documents: items: $ref: '#/components/schemas/ComparedDocumentResult' type: array title: Documents description: Conflicted target documents included in the result payload. type: object required: - matched_documents - conflicted_documents - returned_conflicted_documents - truncated - documents title: ConflictCheckResult ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError ComparedDocumentResult: properties: document_id: type: string title: Document Id description: Matched target document ID. document_title: type: string title: Document Title description: Matched target document title. document_link: anyOf: - type: string - type: 'null' title: Document Link description: Link to the matched target document. conflicts: items: $ref: '#/components/schemas/MetadataConflict' type: array title: Conflicts description: Metadata conflicts detected for this target document. llm_conflicts: items: $ref: '#/components/schemas/LLMConflict' type: array title: Llm Conflicts description: LLM-detected conflicts for this target document. has_conflict: type: boolean title: Has Conflict description: Whether this target document has a conflict. type: object required: - document_id - document_title - conflicts - has_conflict title: ComparedDocumentResult MetadataConflict: properties: rule_id: type: string title: Rule Id description: The rule that detected this conflict. base_field_id: type: string title: Base Field Id description: Field ID on the base document side. target_field_id: type: string title: Target Field Id description: Field ID on the target document side. base_values: items: type: string type: array title: Base Values description: Normalized display values from the base document. target_values: items: type: string type: array title: Target Values description: Normalized display values from the target document. explanation: type: string title: Explanation description: Human-readable explanation of the conflict. type: object required: - rule_id - base_field_id - target_field_id - base_values - target_values - explanation title: MetadataConflict LLMConflict: properties: rule_id: type: string title: Rule Id description: The rule that detected this conflict. summary: type: string title: Summary description: Human-readable description of the detected conflict. base_evidence: type: string title: Base Evidence description: Verbatim excerpt from the base document supporting the conflict. target_evidence: type: string title: Target Evidence description: Verbatim excerpt from the target document supporting the conflict. type: object required: - rule_id - summary - base_evidence - target_evidence title: LLMConflict securitySchemes: HTTPBearer: type: http scheme: bearer ````