Solution
Document search and knowledge bases
Search engines for documents and structured data, with text extraction, lexical or vector indexing, result ranking and permission filtering. Search interfaces and APIs connect them to AI assistants.
Architecture and implementation
Corpus preparation
Extraction of content, metadata and relationships between documents.
Search engines
Lexical and vector search, result ranking and metadata filtering.
Knowledge access
Browsing interfaces and APIs providing applications with access to document collections.
Design decisions
Design of lexical, vector or hybrid search. Lexical search finds exact terms and references; vector search compares semantic similarity. Filters, permissions and document structure constrain passage retrieval.
Illustrative implementation
A query containing a precise reference can prioritise the exact match. A differently worded question can use semantic retrieval. Hybrid search combines these signals before ranking authorised passages.
Engineering outputsDocument index, search engine, filters and retrieval interface
A private platform connects a research agent to a document index and a local Llama model, with retrieval filtered by access permissions. For example, it can support review of a contract file by locating relevant passages in the firm’s documents and reference texts, then preparing an answer with source references.
Docker
.NET
Microsoft Entra ID
Infomaniak
LangChain
Linux
Llama (Meta)
Model Context Protocol
Microsoft 365
PostgreSQL
Python
Components and flows
- Extraction of Microsoft 365 documents and reference collections, followed by text and vector indexing in PostgreSQL
- LangChain agent using a Llama model and read-only MCP search tools, with permission filtering and bounded tool calls
- Available context checked before generation, with references presented in a .NET application
A platform connects mobile data collection and Salesforce CRM to a PostgreSQL warehouse, with Tableau analytics and multilingual document search. One application is a programme operating across several countries, bringing locally collected information together with financial records and related documentation in different languages.
- Docker
- .NET
- Infomaniak
Kotlin- LangChain
- Microsoft 365
n8n- PostgreSQL
- Python
Salesforce
Tableau
Components and flows
- Mobile collection through a .NET API and Salesforce CRM integration with programme data
- Python pipelines feeding a PostgreSQL warehouse, with Tableau analytics and API access
- Multilingual search in Microsoft 365 documents, using LangChain and an Infomaniak model API
Development and integration
- Document extraction and indexing
- Semantic and hybrid retrieval
- Metadata, versions and references
- Search interfaces and RAG integration
Systems involved
- Document-management systems and files
- Relational databases and vector indexes
- Portals, applications and assistants
Service lineArtificial intelligence →
To go deeper
A versioned knowledge base for teams and AI assistants
Approved sources, their history and controlled updates determine a knowledge base’s reliability. Text files can make that chain easier to inspect and maintain.
Designing retrieval, tools and controls for an AI agent
RAG, loops and graphs address different decisions. One supplier dossier shows their roles and the conditions that justify each component.
Discuss your project
A discussion of your project’s design, development and production deployment.