← All agents

AI & research · One purpose, multiple implementations

Create AI-Ready Vector Datasets for LLMs with Bright Data, Gemini & Pinecone

Adapt the published “Create AI-Ready Vector Datasets for LLMs with Bright Data, Gemini & Pinecone” workflow to other implementations while preserving its documented behavior.

The source contains 16 executable nodes and 17 connections. This draft is derived from the n8n export; it needs a human-reviewed purpose, input/output contract, and behavioral tests before a port can claim equivalence.

Open agent files on GitHub ↗

Shared workflow

This initial Mermaid diagram shows observed connections from the n8n source, including model and tool dependencies. Unresolved connections are listed under Evidence. It is a starting point for the shared design; it does not execute the agent or establish correctness.

Rendering the workflow diagram…

Read the Mermaid source
flowchart LR
  n0["When clicking #8216;Test workflow#8217;"]
  n1["AI Agent"]
  n2["Pinecone Vector Store"]
  n3["Embeddings Google Gemini"]
  n4["Default Data Loader"]
  n5["Recursive Character Text Splitter"]
  n6["Google Gemini Chat Model1"]
  n7["Google Gemini Chat Model2"]
  n8["Google Gemini Chat Model"]
  n9["Structured Output Parser"]
  n10["Set Fields - URL and Webhook URL"]
  n11["Make a web request"]
  n12["Structured JSON Data Formatter"]
  n13["Webhook for structured data"]
  n14["Webhook for structured AI agent response"]
  n15["Information Extractor with Data Formatter"]
  n1 -->|"main out 0 to in 0"| n2
  n1 -->|"main out 0 to in 0"| n14
  n11 -->|"main out 0 to in 0"| n12
  n11 -->|"main out 0 to in 0"| n15
  n4 -->|"ai_document out 0 to in 0"| n2
  n3 -->|"ai_embedding out 0 to in 0"| n2
  n8 -->|"ai_languageModel out 0 to in 0"| n15
  n9 -->|"ai_outputParser out 0 to in 0"| n1
  n6 -->|"ai_languageModel out 0 to in 0"| n1
  n7 -->|"ai_languageModel out 0 to in 0"| n12
  n12 -->|"main out 0 to in 0"| n13
  n10 -->|"main out 0 to in 0"| n11
  n10 -->|"main out 0 to in 0"| n13
  n10 -->|"main out 0 to in 0"| n14
  n5 -->|"ai_textSplitter out 0 to in 0"| n4
  n0 -->|"main out 0 to in 0"| n10
  n15 -->|"main out 0 to in 0"| n1
Read the specification and unresolved requirements ↗

Implementations

Each implementation shares the agent’s purpose. Available source, planned ports, and verified results are labeled separately.

Plain Python

Planned · no code yet

Read the implementation plan ↗

Pydantic AI

Planned · no code yet

Read the implementation plan ↗

CrewAI Flow

Planned · no code yet

Read the implementation plan ↗

CrewAI Crew

Planned · no code yet

Read the implementation plan ↗

LangGraph

Planned · no code yet

Read the implementation plan ↗

Build or operate with an assistant

Each prompt includes separate build and operating instructions tailored to this agent. They are untested instructions, not working implementations. Check the chosen product’s actual capabilities before using it.

Evidence and remaining work

The bulk collection has publication checks, not live-service testing. Diagrams and prompts are documentation. A port needs reviewed schemas, fixtures, actual execution results, and explicit limits before claiming equivalent behavior.

  • Define input/output schemas and expected outputs.
  • Review source expressions, external actions, and failure behavior.
  • Determine whether model judgment is required or deterministic rules suffice.

Curated by Nik Bear Brown. Preserve each implementation’s original attribution and license. These source templates are separate from the audited Claude directory.