June
6/30/2025
Page-level Chunking in Datastore Configuration OptionsContextual AI now supports a new page-level chunking mode that preserves slide and page boundaries for more accurate, context-aware retrieval in RAG workflows.
Page-level chunking mode optimizes parsing for page-boundary-sensitive documents. Instead of splitting content purely by size or heading structure, this mode ensures each page becomes its own retrieval-preserving chunk unless the maximum chunk size is exceeded.
This is particularly effective for slide decks, reports, and other page-oriented content, where the meaning is closely tied to individual pages.
Page-level chunking joins existing segmentation options including heading-depth, heading-greedy, and simple-length.
To enable, set chunking_mode = "page" when configuring a
datastore via theingest document APIor via the UI.
6/2/2025
Query Reformulation & DecompositionContextual AI now supports query reformulation and decomposition, enabling agents to rewrite, clarify, and break down complex or ambiguous user queries.
Query reformulation allows agents to rewrite or expand user queries to better match the vocabulary and structure of your corpus. This is essential when user queries are ambiguous, underspecified, or contain terminology not aligned with the domain.
Decomposition automatically determines whether a query should be split into smaller sub-queries. Each sub-query undergoes its own retrieval step before results are merged into a final ranked set.
Common reformulation use cases include:
- Aligning queries with domain-specific terminology
- Making implicit references explicit
- Adding metadata or contextual tags to guide retrieval
Enable these features via Query Reformulation in the agent settings UI, or via the Agent API.
May
5/29/2025
Optimize parsing and chunking strategies via Datastore configurationContextual AI has released new advanced datastore configuration options that let developers fine-tune parsing, chunking, and document processing workflows to produce highly optimized, use-case-specific RAG-ready outputs.
Today, Contextual AI announces the release of advanced datastore configuration options, enabling developers to optimize document processing for RAG-ready outputs tailored to their specific use cases and document types.
Clients can now customize parsing and chunking workflows to maximize RAG performance. Configure heading-depth chunking for granular hierarchy context, use custom prompts for domain-specific image captioning, enable table splitting for complex structured documents, and set precise token limits to optimize retrieval quality.
These configuration options ensure your documents are processed optimally for your RAG system – whether you’re working with technical manuals requiring detailed hierarchical context, visual-heavy documents needing specialized image descriptions, or structured reports with complex tables.
To get started, simply use our updated Agent API and datastore UI with the new configuration parameters to customize parsing and chunking behavior for your specific documents and use cases.
5/20/2025
Chunk viewer for document inspectionContextual AI introduces the Chunk Inspector, a visual debugging tool that lets developers inspect and validate document parsing and chunking results to ensure their content is fully RAG-ready.
Today, Contextual AI announces the release of the Chunk Inspector, a visual debugging tool that allows developers to examine and validate document parsing and chunking results.
Clients can now inspect how their documents are processed through our extraction pipeline, viewing rendered metadata, extracted text, tables or image captioning results for each chunk. This transparency enables developers to diagnose extraction issues, optimize chunking configurations, and ensure their documents are properly RAG-ready before deployment.
The Chunk Inspector provides immediate visibility into how your datastore configuration affects document processing, making it easier to fine-tune parsing and chunking settings for optimal retrieval performance.
To get started, simply navigate to the Chunk Inspector in your datastore UI after ingesting a document to review the extraction and chunking results.
5/13/2025
Document Parser for RAG now Generally AvailableContextual AI has launched a new Document Parser for RAG, a powerful /parse API that delivers highly accurate, hierarchy-aware understanding of large enterprise documents—dramatically improving retrieval quality across complex text, tables, and diagrams.
Today, Contextual AI announces the Document Parser for RAG with our separate /parse component API, enabling enterprise AI agents to navigate and understand large and complex documents with superior accuracy and context awareness.
The document parser excels at handling enterprise documents through three key innovations: document-level understanding that captures section hierarchies across hundreds of pages, minimized hallucinations with confidence levels for table extraction, and superior handling of complex modalities such as technical diagrams, charts, and large tables. In testing with SEC filings, including document hierarchy metadata in chunks increased the equivalence score from 69.2% to 84.0%, demonstrating significant improvements in end-to-end RAG performance.
Get started today for free by creating a Contextual AI account. Visit the Components tab to use the Parse UI playground, or get an API key and call the API directly. We provide credits for the first 500+ pages in Standard mode (for complex documents that require VLMs and OCR), and you can buy additional credits as your needs grow. To request custom rate limits and pricing, please contact us. If you have any feedback or need support, please email parse-feedback@contextual.ai.
March
3/24/2025
Groundedness scoring of model responses now Generally AvailableContextual AI now offers groundedness scoring, a feature that evaluates how well each part of an agent’s response is supported by retrieved knowledge, helping developers detect and manage ungrounded or potentially hallucinated claims with precision.
Today, Contextual AI launched groundedness scoring for model responses.
Ensuring that agent responses are supported by retrieved knowledge is essential for RAG applications. While Contextual’s Grounded Language Models already produce highly grounded responses, groundedness scoring adds an extra layer of defense against hallucinations and factual errors.
When users query an agent with groundedness scores enabled, a specialized model automatically evaluates how well claims made in the response are supported by the knowledge. Scores are reported for individual text spans allowing for precise detection of unsupported claims. In the platform interface, the score for each text span is viewable upon hover and ungrounded claims are visually distinguished from grounded ones. Scores are also returned in the API, enabling developers to build powerful functionality with ease, like hiding ungrounded claims or adding caveats to specific sections of a response.
To get started, simply toggle “Enable Groundedness Scores” for an agent in the “Generation” section of the agent configuration page, or through the agent creation or edit API. Groundedness scores will automatically be generated and displayed in the UI, and returned as part of responses to /agent//query requests.
3/21/2025
Metadata ingestion & document filteringContextual AI now supports document-level metadata ingestion and metadata-based filtering, enabling developers to target queries by attributes like author, date, department, or custom fields for more precise and relevant retrieval.
Today, Contextual AI announces the release of document metadata ingestion and allows for metadata-based filtering during queries.
Clients can now narrow search results using document properties like author, date, department, or any custom metadata fields, delivering more precise and contextually relevant responses.
To get started, simply use our ingest document and update document metadata APIs to add metadata to documents. Once done, use our document filter in the query API to filter down results.
Contextual AI now supports ingesting DOC(X) and PPT(X) files, allowing RAG agents to seamlessly use Microsoft Office documents as part of their retrieval corpus.
Today, Contextual AI announces the release of the support of DOC(X) and PPT(X) files for ingestion into datastore.
This enables clients to leverage Microsoft Office documents directly in their RAG agents, expanding the range of content they can seamlessly incorporate.
To get started, use our document API or our user interface to ingest new files.
3/17/2025
Filtering by reranker relevance score now Generally AvailableContextual AI now allows users to filter retrieved chunks by reranker relevance score, giving them more precise control over which chunks are used during response generation via a new
reranker_score_filter_threshold setting in the Agent APIs and UI.
Today, Contextual AI announces support for filtering retrieved chunks based on the relevance score assigned by the reranker.
The ability to filter chunks based on relevance score gives users more precision and control in ensuring that only the most relevant chunks are considered during response generation. It is an effective alternative or complement to using the filter_prompt for a separate filtering LLM.
To get started, use the reranker_score_filter_threshold parameter in the Create/Edit Agent APIs and in the UI.
3/11/2025
Instruction-following reranker now Generally AvailableA new reranker that uses instructions and intent signals is now GA.
The instruction-following reranker ranks chunks based not only on the query but also on system-level prompts and intent signals, improving retrieval precision.
3/4/2025
Grounded Language Model now Generally AvailableThe Grounded Language Model is now GA.
GLM provides retrieval-anchored generation designed specifically for enterprise RAG applications, improving factuality and stability.
3/3/2025
Advanced parameters now Generally AvailableAdvanced generation controls are now available across agents.
You can now configure decoding parameters such as semantic temperature, reasoning style, and groundedness sensitivity for more predictable output behavior.
February
2/10/2025
Agent-level entitlements now Generally AvailableFine-grained agent permissions are now GA.
Organizations can now restrict access to specific agents, define who can edit or query them, and enforce role-aligned usage boundaries.
The Users API is now GA.
Provides programmatic user management, including permissions, access control, and identity lifecycle integration.
The Metrics API is now available for production use.
Exposes programmatic analytics including usage metrics, latency profiles, groundedness trends, and retrieval performance data.
Agents can now maintain conversational state across turns.
Multi-turn context enables more natural dialog patterns, reference resolution, and ongoing conversational workflows.
Agents can now connect to multiple datastores—and datastores can serve multiple agents.
This reduces ingestion duplication, enables cross-domain retrieval, and supports cleaner information architecture.
Agents can now ingest and retrieve multimodal content.
Early preview includes basic image parsing, multimodal embeddings, and multimodal retrieval pipelines.
Agents can now work with structured datasets.
Early support includes ingestion of tables, schema-defined objects, and CSV datasets, enabling hybrid retrieval across structured and unstructured sources.