Advanced RAG

A sequential approach that refines retrieval results through multiple phases.

How It Works:

1. First stage performs efficient but less precise retrieval (e.g., BM25 keyword search)
2. Second stage applies more intensive semantic filtering on first-stage results
3. Final stage re-ranks candidates using cross-encoders or other precise methods
4. Only the highest quality content is passed to the LLM

An iterative approach that breaks down complex queries and retrieves information in stages.

How It Works:

1. Complex query is broken down into simpler sub-questions
2. Each sub-question is processed through its own retrieval cycle
3. Results from sub-questions are collected and synthesized
4. Final answer incorporates information from all retrieval paths

An approach that generates ideal “hypothetical” documents before retrieval to improve query understanding.

How It Works:

1. LLM expands the user’s query into a hypothetical “ideal document” that would answer it
2. This expanded representation is embedded and used for retrieval
3. The approach bridges terminology gaps between queries and documents
4. Retrieved documents better match the user’s actual intent

Integrates structured knowledge graphs with traditional document retrieval.

How It Works:

1. Identifies entities and relationships in the user query
2. Navigates a knowledge graph to find relevant entities and connections
3. Retrieves both structured data (from the graph) and unstructured content (from documents)
4. Provides context that includes both factual relationships and detailed explanations

Incorporates reasoning and self-critique to improve retrieval quality.

How It Works:

1. Performs initial retrieval and drafts a response
2. Evaluates its own response for gaps, contradictions, or uncertainties
3. Identifies additional information needed to address issues
4. Conducts focused retrieval to fill those gaps
5. Revises the response based on complete information

Using Prisme.ai’s built-in advanced configuration options.

Available advanced options include:

• Multi-stage retrieval configuration
• Query preprocessing settings
• Context handling parameters
• Response generation strategies

This approach is ideal for implementing moderately advanced RAG architectures without requiring coding expertise.

Creating custom RAG workflows using the AI Builder’s product.

AI Builder enables:

• Visual workflow construction
• Custom processing steps
• Integration with other systems
• Complex decision logic

This approach is ideal for implementing sophisticated RAG architectures without extensive coding while maintaining high customization flexibility.

Building highly specialized RAG systems using code and Prisme.ai’s APIs.

Custom development allows:

• Implementing cutting-edge architectures
• Integrating proprietary algorithms
• Creating highly specialized workflows
• Maximum control over the entire process

This approach is ideal for organizations with unique requirements and technical resources to implement highly specialized RAG systems.

Provide custom-retrieved context chunks while letting AI Knowledge handle prompt generation and LLM interaction.

Response Format:

{
  "chunks": [
    {
      "value": {
        "content": "First chunk content that will be injected within LLM prompt",
        "knowledgeId": "Corresponding AIK document id"
      }
    },
    {
      "value": {
        "content": "Second chunk content...",
        "knowledgeId": "Another document id"
      }
    }
  ]
}

Ideal For:

• Custom retrieval strategies
• External knowledge sources
• Specialized context processing
• Dynamic information integration

Take control of the entire prompt while letting AI Knowledge handle the LLM interaction.

Response Format:

{
  "prompt": [
    {
      "role": "system",
      "content": "You are an assistant ... \n Context: ... \n"
    },
    {
      "role": "user",
      "content": "How ... "
    }
  ]
}

Ideal For:

• Specialized prompt engineering
• Custom context formatting
• Chain-of-thought implementation
• Domain-specific instruction tuning

Bypass the entire RAG and LLM process by providing the final answer directly.

Response Format:

{
  "answer": "This is the complete answer that will be shown to the user..."
}

Ideal For:

• Integration with specialized AI systems
• Pre-computed responses
• Multi-agent architectures
• Advanced processing pipelines

Customize AI parameters while letting AI Knowledge handle the rest of the process.

Response Format:

{
  "aiParameters": {
    "model": "gpt-4",
    "prompt": "...",
    "max_tokens": 5000,
    "temperature": 0.9,
    "history": false
  }
}

Ideal For:

• Dynamic model selection
• Context-aware parameter tuning
• Adaptive temperature setting
• Query-specific customization

Provide custom evaluation scores for test results.

Response Format:

{
  "analysis": "Evaluation text summary",
  "score": "2",
  "context": "1.5"
}

Ideal For:

• Specialized evaluation criteria
• Domain-specific quality assessment
• Custom benchmarking
• Comparative analysis