--- title: "Chat with the GitHub API spec stored in Pinecone with OpenAI" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/011bf7a2-20a7-46e9-96fd-3944989eb520" updated: "2026-11-12" --- # Chat with the GitHub API spec stored in Pinecone with OpenAI > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow that answers questions about the GitHub REST API. It downloads GitHub’s OpenAPI description, stores it in Pinecone as OpenAI embeddings, and lets an AI Agent search it from a chat window. Chat with the GitHub API spec stored in Pinecone with OpenAI is an n8n workflow in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow is a chatbot that answers questions about the GitHub REST API from its official specification. One part downloads the specification, cuts it into pieces and saves each piece in a Pinecone index as an OpenAI embedding. The other part is a chat window, where an AI Agent finds the best matching pieces and answers from them. Fourteen nodes do the work, beside three sticky notes. ### Who it suits Developers and technical writers who want a working example of retrieval augmented generation in n8n, and anyone who wants to ask about GitHub’s API without reading its reference. Skip it if you need answers from your own documents as they stand. You would change what it downloads first. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Developers | Ask how an endpoint works without searching the reference | A developer asks how to list the issues of a repository and gets the path and its parameters. | | Documentation | Technical writers | Study the pattern before building a bot for their own docs | A writer swaps the download for the company’s API file and keeps the rest. | | Education | Course leads | Show students retrieval augmented generation with a real file | A lead runs the indexing in class, then asks the chat three questions. | | Support | Integration engineers | Answer customers’ API questions faster | An engineer asks which call creates a gist and reads the matching passage. | You need a little n8n: import a file, add an OpenAI and a Pinecone credential, create an index and run the indexing once. ### Where to use it Any n8n that can reach OpenAI, Pinecone and GitHub’s file host will run it. The chat opens inside n8n, so the answers stay in your editor. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - Your own documents: change the address in \`HTTP Request\` to another JSON or text file - A second index: point both Pinecone nodes at it to keep topics apart ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Two accounts are involved. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | OpenAI | An API key, for an OpenAI credential | | Pinecone | An account, an API key and an index with 1536 dimensions, for a Pinecone credential | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. In Pinecone, create an index with 1536 dimensions, the size of OpenAI’s `text-embedding-3-small` embeddings. 3. Add an OpenAI credential and select it in `Generate Embeddings`, `Generate User Query Embedding`, `OpenAI Chat Model` and `OpenAI Chat Model1`. 4. Add a Pinecone credential, select it in `Pinecone Vector Store` and `Pinecone Vector Store (Querying)`, and choose your index in both. 5. Click Test workflow on the manual trigger and wait for it to finish. The first run takes a while, since the file is about 14 MB. 6. Open the chat and ask a question. ### How to use it Once the index is full, open the chat panel and ask about the GitHub API, for example how to list a repository’s issues. The agent keeps the last few messages of a chat as memory. Run the indexing again only when you change the file or the index. What to change for a different result | To change | Where | | --- | --- | | The file | The address in \`HTTP Request\` | | The index | Pinecone Index in both Pinecone nodes | | The agent’s instructions | System Message in \`AI Agent\` | | When the agent searches | Description in \`Vector Store Tool\` | | How many pieces come back | Limit in \`Vector Store Tool\`, which starts at 4 | | The models | Model in \`OpenAI Chat Model\` and \`OpenAI Chat Model1\` | ### Example A developer asks the chat how to list the issues of a repository. The agent calls the vector store tool, which turns the question into an embedding and asks Pinecone for the four closest pieces. The tool’s own model reads those pieces and answers, and the agent passes the answer on. The reply names the path for listing issues and says that open issues are returned by default. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. This one has two starts. The manual start fills the index, and the chat start answers questions from it. Run the first once, then open each box of the second to see where an answer comes from. **For experts.** Both Pinecone nodes need the same index and the same embedding model, or the vectors will not match. Mindket’s copy sets `text-embedding-3-small` on both embedding nodes outright, where the original left it to the node’s default. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`HTTP Request\` | GET of GitHub’s OpenAPI description from its public repository | The file is 14,263,438 bytes and comes back as plain text | | \`Default Data Loader\` and \`Recursive Character Text Splitter\` | Turn the downloaded item into pieces | Pieces are about 1,000 characters with no overlap, so the file gives roughly 14,000 of them | | \`Pinecone Vector Store\` | Insert mode, with \`Generate Embeddings\` | It adds the pieces each time it runs and clears nothing unless you switch on Clear Namespace | | \`AI Agent\` | Agent 1.7 with a system message, a window memory and one tool | It runs as a Tools Agent | | \`Vector Store Tool\` | Answers from the Pinecone store through \`OpenAI Chat Model1\` | Its name and description tell the agent when to use it | | \`Pinecone Vector Store (Querying)\` | Retrieve mode, with \`Generate User Query Embedding\` | It feeds the tool, and the tool returns up to 4 pieces | ### Good to know The indexing run is large for a first try, and a model change was needed. - Models: OpenAI’s deprecations page, read on 12 November 2026, lists gpt-5-mini, the node’s old default, as shutting down on 11 December 2026 with \`gpt-5.6-terra\` as the replacement. The original named no model, so Mindket’s copy sets \`gpt-5.6-terra\` for the agent and \`gpt-6-luna\` for the tool’s own model, which only reads the pieces - Why not \`gpt-6-luna\` for the agent: its model page says Chat Completions supports function calling only with reasoning effort off, and an agent needs function calling - Size: the file splits into roughly 14,000 pieces, each embedded and stored, so the first run takes a while and costs a little on both services - Run it once: a second indexing run stores every piece again, unless Clear Namespace is on in \`Pinecone Vector Store\` - Index size: an index that does not have 1536 dimensions refuses the vectors, so check it before the first run - Memory: the agent’s window memory lives in n8n’s own memory, is cleared after an idle hour and does not suit queue mode - Empty pickers: the author’s own Pinecone index is gone, so choose yours - Billing: each question costs one agent call and one call inside the tool, plus an embedding, and each is billed by its provider - Your data: your questions go to OpenAI and Pinecone, and the file you index goes to both too - Credentials: the JSON holds none, so add the OpenAI and Pinecone credentials yourself ## README ```markdown # Chat with the GitHub API spec stored in Pinecone with OpenAI An n8n workflow that is a chatbot for the GitHub REST API. One part downloads GitHub's OpenAPI description of that API, cuts it into pieces and saves each piece in a Pinecone index as an OpenAI embedding. The other part is a chat window where an AI Agent finds the best matching pieces and answers from them. ## What is inside - `workflow.json`: the workflow as n8n exports it, fourteen working nodes and three sticky notes. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy - The Pinecone index name was the author's own (`n8n-demo`). Both Pinecone nodes now show an empty index picker, and the Querying node says `retrieve` outright for its mode. - The original named no chat model, so n8n's default applied. Mindket's copy sets `gpt-5.6-terra` on `OpenAI Chat Model` (the agent) and `gpt-6-luna` on `OpenAI Chat Model1` (the vector store tool). See Good to know. - Both embedding nodes now say `text-embedding-3-small` outright, so the two Pinecone nodes always use the same model. - The three sticky notes were rewritten, and mention the new models and the index size. ## Before you start - An n8n instance, on n8n Cloud or your own server. - An OpenAI API key. - A Pinecone account, an API key and an index with 1536 dimensions. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. In Pinecone, create an index with 1536 dimensions, the size of `text-embedding-3-small` embeddings. 3. Add an OpenAI credential and select it in `Generate Embeddings`, `Generate User Query Embedding`, `OpenAI Chat Model` and `OpenAI Chat Model1`. 4. Add a Pinecone credential, select it in `Pinecone Vector Store` and `Pinecone Vector Store (Querying)`, and choose your index in both. 5. Click Test workflow on the manual trigger and wait for it to finish. The first run takes a while, since the file is about 14 MB. 6. Open the chat and ask a question. ## How a run goes Indexing, from the manual trigger: 1. `HTTP Request` downloads GitHub's OpenAPI description from its public repository. 2. `Default Data Loader` and `Recursive Character Text Splitter` cut it into pieces of about 1,000 characters. 3. `Generate Embeddings` turns each piece into a vector, and `Pinecone Vector Store` (Insert) saves it. Chatting, from the chat trigger: 1. `When chat message received` hands the message to `AI Agent`, which has a window memory and a system message. 2. The agent calls `Vector Store Tool` when a question needs the specification. 3. `Generate User Query Embedding` embeds the question, and `Pinecone Vector Store (Querying)` returns the 4 closest pieces. 4. `OpenAI Chat Model1` reads those pieces for the tool, and `OpenAI Chat Model` writes the final reply. ## Change the look - The file: the address in `HTTP Request`. - The index: Pinecone Index in both Pinecone nodes. - The agent's instructions: System Message in `AI Agent`. - When the agent searches: Description in `Vector Store Tool`. - How many pieces come back: Limit in `Vector Store Tool`. ## Good to know - OpenAI's deprecations page, read on 12 November 2026, lists `gpt-5-mini` as shutting down on 11 December 2026 with `gpt-5.6-terra` as the replacement. That page for `gpt-6-luna` says Chat Completions supports function calling only with reasoning effort off, so the agent uses `gpt-5.6-terra`. - The file splits into roughly 14,000 pieces, so the first run takes a while. - A second indexing run stores every piece again, unless Clear Namespace is on in `Pinecone Vector Store`. - An index that does not have 1536 dimensions refuses the vectors. - Your questions and the file you index go to OpenAI and Pinecone. ``` ## What is in it 3 files, 14 KB, downloaded as a zip. ```text NOTICE.md 706 B README.md 4 KB workflow.json 9 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 5 steps, starting by hand or on a chat message - AI: 2 steps call an AI model: Pinecone Vector Store and AI Agent - Sign-ins: Signs in to: Pinecone and OpenAI - API keys: No API key is left in the file - Step types: Mindket’s checker reads all 5 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/011bf7a2-20a7-46e9-96fd-3944989eb520) - [Its page on Mindket](https://mindket.com/p/011bf7a2-20a7-46e9-96fd-3944989eb520)