> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pastures.farm/llms.txt
> Use this file to discover all available pages before exploring further.

# The Oracle Corpus

> 48,000+ real issue resolutions from 13 open-source repositories powering grounded AI diagnostics.

The Oracle corpus is the knowledge base behind Rancher Oracle. It indexes **48,000+ real issue resolutions** from 13 open-source repositories across the Rancher and Kubernetes ecosystem.

## Indexed repositories

| Repository                          | Domain                       |
| ----------------------------------- | ---------------------------- |
| `rancher/rancher`                   | Rancher Manager              |
| `k3s-io/k3s`                        | K3s lightweight Kubernetes   |
| `rancher/rke2`                      | RKE2 Kubernetes              |
| `harvester/harvester`               | Harvester HCI                |
| `longhorn/longhorn`                 | Longhorn distributed storage |
| `neuvector/neuvector`               | NeuVector container security |
| `rancher/fleet`                     | Fleet GitOps                 |
| `rancher/system-upgrade-controller` | Automated upgrades           |
| `rancher/local-path-provisioner`    | Local path storage           |
| `rancher/webhook`                   | Rancher admission webhooks   |
| `rancher/charts`                    | Helm charts                  |
| `rancher/kontainer-driver-metadata` | Kubernetes version metadata  |
| `rancher/norman`                    | Rancher API framework        |

## What's indexed

The corpus includes:

* **Issue resolutions** — closed issues with confirmed fixes
* **Pull requests** — merged PRs with linked issues
* **Discussions** — community Q\&A with accepted answers
* **Release notes** — version-specific changes and known issues

## How indexing works

<Steps>
  <Step title="Ingestion">
    Issues, PRs, discussions, and release notes are collected from each repository via the GitHub API.
  </Step>

  <Step title="Chunking">
    Documents are split into semantically meaningful chunks — preserving context around error messages, stack traces, and configuration snippets.
  </Step>

  <Step title="Embedding">
    Each chunk is embedded using a transformer model that captures the semantic meaning of Kubernetes errors, configuration patterns, and troubleshooting procedures.
  </Step>

  <Step title="Storage">
    Embeddings are stored in a vector database optimized for high-recall semantic search.
  </Step>

  <Step title="Retrieval">
    On query, semantic search retrieves the top-k matching chunks, which are passed as context to the LLM for grounded response generation.
  </Step>
</Steps>

## Why embeddings matter

Traditional keyword search fails for Kubernetes troubleshooting. An error like `failed to create pod sandbox` has dozens of root causes — CNI misconfiguration, disk pressure, container runtime issues, and more.

Semantic embeddings capture the *meaning* behind error messages and stack traces, not just the keywords. This means Oracle can match a user's error against resolutions that describe the same underlying problem in different terms.

## Corpus updates

The corpus is updated regularly as new issues are resolved across the indexed repositories. New resolutions, PRs, and discussions are ingested, chunked, embedded, and added to the vector database on a recurring schedule.

<Info>
  Enterprise customers can request custom corpus additions — internal runbooks, private repositories, or domain-specific documentation indexed alongside the public corpus.
</Info>