LLM Chat History
Chain LLM nodes with chat history in PixelFlow to build multi-turn conversations, branching dialogues, and conversational AI pipelines — visually.
Chat history lets LLM nodes remember previous turns. Connect one LLM node's output to the next node's Chat History input and the conversation context carries forward — the foundation for chatbots, agents, and any multi-turn dialogue.
Screenshot coming soon
A two-turn conversation as a graph
/images/pixelflow/guides/llm-chat-history.webp
How it works
Language model nodes expose a Chat History input alongside the prompt:
- First turn — the first LLM node takes your prompt and generates a response. No history is connected.
- Carrying context — connect that node's output to the next LLM node's Chat History input. The full exchange (prompt + response) travels with it.
- Subsequent turns — each node in the chain receives the entire conversation so far, so responses stay coherent across turns.
Branching conversations
Connect one LLM node's output to the Chat History input of several downstream nodes and each becomes an independent branch of the conversation — same shared context, different continuations. Use it to:
- A/B test prompts against identical context
- Explore multiple dialogue paths side by side
- Compare different models continuing the same conversation
Use cases
- Chatbots and assistants that remember the conversation
- Multi-step reasoning — draft, critique, revise as separate turns
- Content pipelines — interview-style generation where each question builds on previous answers
- Education tools — adaptive dialogues that respond to earlier exchanges
Combining chat history with vision inputs lets a conversation reference images: caption an image in turn one, refine the description in turn two.
Pinning and Caching
Pin nodes in PixelFlow to cache their output across runs — skip expensive re-execution, iterate faster, and save credits while you refine a workflow.
Fan-Out and Parallel Runs
Run a model once per item with fan-out edges in PixelFlow, then gather results with collect — visual map/reduce for AI: batch images, compare models, scale prompts.