Agentic Service Discovery

Resources

P

Pinecone

by Pinecone Systems, Inc.

Upsert and query vector embeddings in Pinecone for retrieval-augmented generation (RAG), semantic search, and similarity matching in agent workflows.

DatabaserGratis / BetaltAPI-nøglevector-databaseembeddingsragsemantic-searchaisimilarity

Sådan bruger agenter Pinecone

  • ✓Agent queries a Pinecone index with an embedding to retrieve the most relevant document chunks for RAG before calling an LLM
  • ✓Agent upserts new document embeddings into an index when new content is ingested into a knowledge base
  • ✓Agent deletes outdated vectors from the index when source documents are updated or removed
  • ✓Agent performs semantic similarity search to find the most relevant past interactions or support tickets
  • ✓Agent checks index stats to verify that embeddings were successfully ingested before proceeding
  • ✓Agent creates a new namespace in the index to partition vectors by tenant, project, or document type
  • ✓Agent fetches specific vectors by ID to inspect their metadata as part of a debugging or audit workflow

Agenthandlinger

Query VectorsSearch an index for the most similar vectors to a query vector (nearest neighbour search).

Input: indexName, vector, topK, namespace, filter, includeMetadata, includeValues

Returnerer: matches, matchCount, topScore, namespace

Upsert VectorsInsert or update vectors in a Pinecone index.

Input: indexName, vectors, namespace

Returnerer: upsertedCount, success

Fetch VectorsRetrieve vectors by their IDs from a Pinecone index.

Input: indexName, ids, namespace

Returnerer: vectors, fetchedCount, namespace

Delete VectorsDelete specific vectors by ID, or all vectors in a namespace.

Input: indexName, ids, filter, deleteAll, namespace

Returnerer: success

Describe Index StatsRetrieve statistics about a Pinecone index including vector counts and dimension.

Input: indexName, filter

Returnerer: totalVectorCount, dimension, namespaces, stats

List IndexesRetrieve all Pinecone indexes in the project.

Returnerer: indexes, indexCount

Create IndexCreate a new serverless Pinecone index.

Input: name, dimension, metric, cloud, region

Returnerer: indexName, host, index

Eksempel på workflows

1

RAG knowledge base query

An agent embeds a user query, queries Pinecone for the top-5 relevant chunks, and passes them as context to an LLM node.

2

Document ingestion pipeline

When new documents are uploaded, an agent chunks and embeds them, then upserts the vectors into Pinecone for future retrieval.

Om Pinecone

Leverandør
Pinecone Systems, Inc.
Pris Tjek altid detaljer med udbyderen
Gratis / Betalt — Free Starter plan includes 2GB storage and 5 serverless indexes. Paid plans are usage-based (storage + read/write units).
Godkendelse
API-nøgle
Hastighedsgrænse Tjek altid detaljer med udbyderen
100 anmodninger / minut
Kompatible noder
AgentResourceInputOutput
Hjemmeside
https://www.pinecone.io

Byg et AI-workflow med Pinecone

Brug Agentic Planner til at designe, visualisere og forbinde Pinecone med dine andre værktøjer.

Åbn Agentic Planner

Relaterede Databaser-værktøjer

M

MySQL

Connect to MySQL databases to query, insert, update, and manage data

P

PostgreSQL

Connect to PostgreSQL databases to query, insert, update, and manage data

M

MongoDB

Connect to MongoDB databases to store, query, and manage document-based data