opencode-rag-plugin 1.3.6 → 1.4.2

package/ReadMe.md

@@ -111,6 +111,33 @@ Running `opencode-rag init` creates the config file `opencode-rag.json` in your
 | `retrieval.topK` | `10` | Default number of chunks fetched per query. |
 | `retrieval.hybridSearch.enabled` | `true` | Enables combined TF×IDF + vector search. |
 
+### Description-Based Embedding (Optional)
+
+When enabled, the indexer uses an LLM to generate natural-language descriptions of code chunks, then combines the description with the raw code for embedding. This captures both semantic meaning (from the description) and code-level similarity (from the code itself), dramatically improving search quality for natural language and code-based queries alike.
+
+```json
+{
+  "description": {
+    "enabled": true,
+    "provider": "ollama",
+    "baseUrl": "http://localhost:11434/api",
+    "model": "qwen2.5:3b",
+    "timeoutMs": 60000,
+    "systemPrompt": "You are a code analysis assistant. Given a code snippet, write a short (2-3 sentence) description of what the code does, its purpose, and key functionality. Focus on semantic meaning that would help someone searching for this code. Do not include code in your response."
+  }
+}
+```
+
+| Option | Default | Description |
+|--------|---------|-------------|
+| `description.enabled` | `true` | Enable description-based embedding. Set to `false` to embed raw code instead. |
+| `description.provider` | `"ollama"` | LLM provider (`"ollama"` or `"openai"`). |
+| `description.model` | `"qwen2.5:3b"` | Model name for description generation. |
+| `description.systemPrompt` | *(see above)* | Customizable system prompt for the LLM. |
+| `description.timeoutMs` | `60000` | Timeout per LLM call. |
+
+The embedded text is formed as `description + "\n\n" + code content`. The description and code are still stored as separate fields in LanceDB. Keyword search continues to use the raw code content. Set `description.enabled` to `false` to disable and embed raw code content instead. If the LLM call fails during indexing, the chunk falls back to embedding raw content with a warning logged.
+
 <details>
 <summary>View Logging Configuration</summary>
 
@@ -155,7 +182,7 @@ After each user message, a `chat.message` hook appends up to 10 relevant file su
 
 ## CLI Interface
 
-The CLI interface (`opencode-rag`) provides full access to build, manage, and search your project's vector database, even without opening OpenCode.
+The CLI interface (`opencode-rag`) provides full access to build, manage, and search your project's vector database, even without using OpenCode.
 This is mainly intended for testing/debugging purposes, but can also be integrated into your own applications or scripts.
 
 ```bash
@@ -174,6 +201,11 @@ opencode-rag query "How is authentication handled?" --top-k 5
 # Show index statistics or clear data
 opencode-rag status
 opencode-rag clear
+
+# Inspect indexed data
+opencode-rag list               # list all indexed files with chunk counts
+opencode-rag show src/auth.ts   # show chunks for a specific file
+opencode-rag dump --limit 50    # dump all chunks (paginated)
 ```
 
 ---

package/dist/cli.d.ts

@@ -1,9 +1,4 @@
 #!/usr/bin/env node
 export declare function removeStaleGlobalPluginRegistrations(homeDir: string, pluginName: string): string[];
-/**
- * Determine whether the CLI should auto-run for the current module.
- * Resolves the first argv entry so symlinked binaries compare against the
- * real file path, and returns false if the path cannot be resolved.
- */
 export declare function shouldAutoRunCli(moduleUrl: string, argv1?: string): boolean;
 export declare function runCli(argv?: string[]): Promise<void>;