feat(embeddings): add OPENAI_BASE_URL support for custom endpoints

Add support for custom OpenAI-compatible API endpoints via OPENAI_BASE_URL
environment variable. This enables using:
- Ollama for local LLM inference
- LiteLLM Proxy for unified model access
- Groq, OpenRouter, and other OpenAI-compatible providers
- Self-hosted models (vLLM, text-generation-inference)

Changes:
- Read OPENAI_BASE_URL from environment in DEFAULT_EMBEDDING_CONFIG
- Update README.md with configuration documentation
- Update CHANGELOG.md with feature entry

Fixes #70

Author: rothnic

CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## [Unreleased]
+
+### Features
+
+* **embeddings:** Add `OPENAI_BASE_URL` support for custom OpenAI-compatible endpoints (e.g., Ollama, LiteLLM) ([#70](https://github.com/PatrickSys/codebase-context/issues/70))
+
 ## [1.8.2](https://github.com/PatrickSys/codebase-context/compare/v1.8.1...v1.8.2) (2026-03-05)
 
 

README.md

@@ -346,6 +346,7 @@ Structured filters available: `framework`, `language`, `componentType`, `layer`
 | ------------------------ | -------------------------- | --------------------------------------------------------------------------------------------- |
 | `EMBEDDING_PROVIDER`     | `transformers`             | `openai` (fast, cloud) or `transformers` (local, private)                                     |
 | `OPENAI_API_KEY`         | -                          | Required only if using `openai` provider                                                      |
+| `OPENAI_BASE_URL`        | `https://api.openai.com/v1` | Custom OpenAI-compatible API endpoint (LiteLLM, Groq, OpenRouter, etc.)                       |
 | `CODEBASE_ROOT`          | -                          | Project root (CLI arg takes precedence)                                                       |
 | `CODEBASE_CONTEXT_DEBUG` | -                          | Set to `1` for verbose logging                                                                |
 | `EMBEDDING_MODEL`        | `Xenova/bge-small-en-v1.5` | Local embedding model override (e.g. `onnx-community/granite-embedding-small-english-r2-ONNX` for Granite) |

src/embeddings/types.ts

@@ -37,5 +37,6 @@ export const DEFAULT_EMBEDDING_CONFIG: EmbeddingConfig = {
   model: DEFAULT_MODEL,
   batchSize: 32,
   maxRetries: 3,
-  apiKey: process.env.OPENAI_API_KEY
+  apiKey: process.env.OPENAI_API_KEY,
+  apiEndpoint: process.env.OPENAI_BASE_URL || 'https://api.openai.com/v1'
 };