← All Workflows

🔍 RAG Pipeline

Retrieval-Augmented Generation using Remember as a document store and Recall as the retriever. ConditionalRouter catches LLM errors gracefully, splitting output into success and error paths.

Nodes 9
Agents 1
Agent ID researcher@localhost
Key Feature ConditionalRouter
Remember Recall PromptTemplate LLM ConditionalRouter

Pipeline Flow

Store docs → search → build RAG prompt → LLM answers → route errors vs. success.

Identity
Setup
researcher@localhost
Store
Remember
doc: agentazall overview
Search
Recall
query: "agentazall"
Build Prompt
PromptTemplate
{a}=question {b}=context
System
SystemPrompt
research assistant
Inference
LLM
temp: 0.3 (factual)
Route
ConditionalRouter
pattern: "LLM_ERROR"
Error
Error Display
matched path
Success
Answer Display
unmatched path
Store & Search Documents Build RAG Prompt LLM + Error Routing Results (Error | Success)

Key Features

📚

File-Based Document Store

Remember stores documents as plain text files with keyword-searchable titles. No vector database needed. Recall retrieves them by keyword match — fast and transparent.

🔄

Error Routing

ConditionalRouter checks for "LLM_ERROR" in the response. If the LLM is down or returns an error, it goes to the error display. Success goes to the answer display. No broken pipes.

🔧

Grounded Answers

The PromptTemplate enforces "answer using ONLY the provided context." The LLM is set to low temperature (0.3) for factual responses. If context doesn't cover the question, it says so.

🚀

Composable Retrieval

Add more Remember nodes to ingest multiple documents. Add more Recall nodes with different queries to search different aspects. Combine results with TextCombine before the LLM.

ConditionalRouter: Two-Path Output

Input: LLM response text
Pattern: "LLM_ERROR" (keyword match)

If matched: → Error Display (red path)
"LLM_ERROR: Connection refused to http://localhost:11434"

If not matched: → Answer Display (green path)
"AgentAZAll supports FTP, email, HTTPS, and local file transport..."