Automating Access to Internal Knowledge and Business Processes Using RAG and a Telegram Bot

🧩 1. Why This Matters: The Problem We Solved

Growing companies with extensive internal documentation often face a common challenge: employees spend too much time searching for information or asking repetitive questions. This reduces productivity and increases the load on support teams.

Typical scenarios:

• A new employee can't find the contract template;
• A manager forgets how to issue an invoice;
• A developer is unsure who should review their code.

🛠️ 2. Solution Architecture Overview

Before diving into the details, here's an overview of our architecture, which includes:

• RAG (Retrieval-Augmented Generation) — a hybrid AI approach combining retrieval and generation;
• Vector storage — for semantically meaningful document retrieval;
• Telegram bot — as the user interface for employees;
• Redmine API — to automate task management and time tracking;
• GitLab — as the living documentation source.

📌 RAG Explained (Haystack)

🧠 3. Preparing the Knowledge Base and Vectorization

The company's internal knowledge was stored as .md files in GitLab. We:

• Automated document extraction;
• Cleaned and preprocessed the content;
• Vectorized the content using sentence-transformers (Learn more);
• Indexed the content in Elasticsearch.

📌 Vector Databases Overview

🤖 4. Telegram Bot — Employee Interface

Employees interact with the bot by asking questions directly in chats:

• "How do I log time for Project Alpha?"
• "Which NDA template should I use?"

If the bot is unsure of the answer, it forwards the question to a support channel.

🔁 5. Self-Learning and Answer Quality Management

Every unanswered question signals a documentation gap.

• We log "unanswered" queries;
• Manually review and tag them;
• Create or update documents;
• Re-index the knowledge base.

📌 RAG Quality Evaluation – OpenAI Cookbook

🧱 6. Redmine Integration

With Redmine API integration, employees can:

• View their assigned tasks;
• Log time directly via the bot;
• Generate invoices;
• Initiate contract preparation.

📌 Redmine API Docs

💬 7. Example Queries

Examples:

🧑: How do I issue an invoice for March?
🤖: Here's the instruction: [link]

🧑: Who should review my pull request?
🤖: Your team lead or a senior developer. More info: [link]

📈 8. Outcomes and Scalability

Results:

• Reduced support load;
• Faster onboarding for new employees;
• Routine processes automated.

Scalability options:

• Integration with Slack, MS Teams;
• Multi-language support;
• Integration with other APIs (CRM, ERP, etc.).

Key Benefits of RAG-Based Knowledge Systems

• Improved productivity: Employees find information faster
• Reduced support load: Fewer repetitive questions to support teams
• Better onboarding: New employees can access knowledge instantly
• Process automation: Routine tasks handled automatically
• Continuous improvement: System learns from unanswered questions

Implementation Best Practices

1. Start with high-value content: Focus on frequently accessed documents
2. Regular updates: Keep knowledge base current and relevant
3. Quality monitoring: Track answer accuracy and user satisfaction
4. Integration planning: Connect with existing tools and workflows
5. User training: Help employees understand how to use the system effectively

🤝 Want Similar Results?

If you'd like to automate your internal knowledge access and streamline business processes, get in touch with us. Let's build it together.

📎 Useful Links

• Haystack: RAG
• Sentence-Transformers
• Pinecone Guide
• RAG Evaluation
• Redmine API
• AI Agents Ecosystem Trends (Anchor: DesignRush) - Industry analysis by our partners at DesignRush