Vector Databases: Pinecone, Weaviate & pgvector · 课时

代理式检索与记忆

探索人工智能代理如何将向量数据库用作长期记忆，并执行迭代式、工具驱动的检索。

代理式检索与记忆 是 CoddyKit 上的免费 Vector Databases: Pinecone, Weaviate & pgvector 课时。这是第 4 节课，共 4 节。你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。这是 Vector Databases: Pinecone, Weaviate & pgvector 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Vector Databases: Pinecone, Weaviate & pgvector 课程共包含 4 节课。

本课时的部分内容尚未翻译，以英文显示。

From Search to Agents

Beyond one-shot RAG, AI agents use vector databases as a persistent memory and as a tool they can query repeatedly while reasoning.

Agent Memory Types

Agents juggle several memory kinds:

Short-term: current conversation
Long-term: facts stored as vectors
Episodic: past interactions and outcomes

Storing Memories

The agent embeds important facts and writes them to the vector store with metadata like timestamp and source.

memory_store.add(
    text='User prefers dark mode',
    metadata={'type': 'preference', 'ts': now}
)

Retrieval as a Tool

The agent decides when to search memory, treating retrieval as a callable tool rather than a fixed pipeline step.

{
  "name": "search_memory",
  "arguments": { "query": "user UI preferences" }
}

Iterative Retrieval

Agents can search, reason, then search again with a refined query — looping until they have enough context. This multi-hop approach answers complex questions.

Self-Querying

A self-querying agent converts a natural request into a structured query with filters, then runs it against the vector store.

# 'recent docs about billing' ->
# filter: topic='billing', published_at > 30d ago

Memory Consolidation

Over time, agents summarize and merge redundant memories to keep the store compact and avoid contradictory facts.

Forgetting & Decay

Not all memories should persist. Apply decay or TTLs so stale or low-value memories are pruned, keeping retrieval relevant.

Relevance + Recency

Agent memory retrieval often blends semantic similarity with recency and importance scores, not just raw distance.

score = w1*similarity + w2*recency + w3*importance

Frameworks & Tooling

Libraries like LangGraph, LlamaIndex, and dedicated memory layers wire vector stores into agent loops with built-in memory management.

The Road Ahead

Agentic retrieval is a leading trend: vector databases evolve from passive search engines into the long-term memory backbone of autonomous AI systems.

Quick Check

Test your agentic retrieval knowledge.

Recap

You learned how agents use vector stores as memory, treat retrieval as a tool, perform iterative self-querying, and manage memory with consolidation, decay, and recency-aware scoring.

常见问题解答

「代理式检索与记忆」课时是免费的吗？

是的 — 「代理式检索与记忆」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Vector Databases: Pinecone, Weaviate & pgvector 课程的其余内容，请升级到 CoddyKit PRO。 Vector Databases: Pinecone, Weaviate & pgvector 课程共包含 4 节课。

「代理式检索与记忆」这节课中我会学到什么？

探索人工智能代理如何将向量数据库用作长期记忆，并执行迭代式、工具驱动的检索。你通过在浏览器中直接运行的动手代码来练习 Vector Databases: Pinecone, Weaviate & pgvector，全天候 AI 导师会在你学习这节课的过程中回答你的问题。

学习 Vector Databases: Pinecone, Weaviate & pgvector 需要有经验吗？

无需任何先前经验。CoddyKit 上的 Vector Databases: Pinecone, Weaviate & pgvector 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。这是第 4 节课，共 4 节。

「代理式检索与记忆」课时需要多长时间？

大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。

我能在这节 Vector Databases: Pinecone, Weaviate & pgvector 课中编写并运行代码吗？

能。每节 Vector Databases: Pinecone, Weaviate & pgvector 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。

此课程中的所有课时

← 返回 Vector Databases: Pinecone, Weaviate & pgvector