OpenAI Configuration
Simili Bot v0.2.0 supports OpenAI as a full alternative to Google Gemini for both embeddings and LLM analysis.
Getting started
1. Get API key
- Go to platform.openai.com
- Sign in with your OpenAI account
- Click Create new secret key
- Copy the generated API key
2. Set up GitHub secret
Store your API key securely:
- Go to repository Settings → Secrets and variables → Actions
- Create secret
OPENAI_API_KEY
- Paste your API key
Add to .github/simili.yaml:
embedding:
provider: "openai"
api_key: "${OPENAI_API_KEY}"
model: "text-embedding-3-small"
dimensions: 1536
llm:
provider: "openai"
api_key: "${OPENAI_API_KEY}"
model: "gpt-5.2"
Configuration reference
Embedding settings
| Property | Type | Description | Required |
|---|
provider | string | Must be "openai" | Yes |
api_key | string | OpenAI API key | Yes |
model | string | Embedding model | No (default: text-embedding-3-small) |
dimensions | number | Must match model output | Yes |
LLM settings
| Property | Type | Description | Default |
|---|
provider | string | Must be "openai" | Inherits from embedding |
api_key | string | OpenAI API key | Inherits from embedding |
model | string | LLM model | gpt-5.2 |
Available models
Embedding models
| Model | Dimensions | Notes |
|---|
text-embedding-3-small | 1536 | Default, cost-efficient |
text-embedding-3-large | 3072 | Highest quality |
text-embedding-ada-002 | 1536 | Legacy, not recommended |
The dimensions value must match the model’s output. Mismatches will cause Qdrant collection errors.
Provider precedence
If both GEMINI_API_KEY and OPENAI_API_KEY are set, Gemini takes priority.
To use only OpenAI:
- Only set
OPENAI_API_KEY (do not set GEMINI_API_KEY), or
- Explicitly configure
provider: "openai" in your simili.yaml
Mixed providers
You can use different providers for embeddings and LLM:
# Use OpenAI for embeddings, Gemini for LLM
embedding:
provider: "openai"
api_key: "${OPENAI_API_KEY}"
model: "text-embedding-3-large"
dimensions: 3072
llm:
provider: "gemini"
api_key: "${GEMINI_API_KEY}"
model: "gemini-2.5-flash"
Common issues & solutions
Invalid API key
Error: Error 401: Incorrect API key provided
Solutions:
- Verify the key is correct from platform.openai.com
- Ensure no extra whitespace in the secret value
- Check the key has not been revoked
Rate limited
Error: Error 429: Rate limit reached
Solutions:
- Reduce worker count during bulk indexing
- Upgrade your OpenAI tier for higher limits
Dimension mismatch
Error: collection dimension mismatch
Make sure dimensions matches the model:
embedding:
model: "text-embedding-3-small"
dimensions: 1536 # Must match!
Next steps
