Skip to content

chore: opensearch embedding model dimension configurability #248

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
akhil-vamshi-konam wants to merge 1 commit into
base: master
Choose a base branch
from
Open

chore: opensearch embedding model dimension configurability #248

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions docs/self-hosting/govern/aws-opensearch-embedding.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -224,10 +224,12 @@ POST /_plugins/_ml/models/<model_id>/_predict

## Configure Plane

Add the deployed model ID to `/opt/plane/plane.env`:
Add the deployed model ID and configuration to `/opt/plane/plane.env`:

```bash
EMBEDDING_MODEL_ID=<model_id>
OPENSEARCH_ML_MODEL_ID=<model_id>
EMBEDDING_MODEL=cohere/embed-v4.0
OPENSEARCH_EMBEDDING_DIMENSION=1536
```

Restart Plane and complete the remaining steps in [Enable Plane AI](/self-hosting/govern/plane-ai#configure-an-embedding-model).
77 changes: 40 additions & 37 deletions docs/self-hosting/govern/environment-variables.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,14 +227,15 @@ Use these when routing requests through self-hosted gateways, proxies, or compat

These settings are required for semantic search and Plane AI Chat. Configure one of the following options.

| Variable | Description | Required |
| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------- |
| **EMBEDDING_MODEL_ID** | ID of an existing embedding model deployed in OpenSearch (works with both self-hosted and AWS OpenSearch) | Conditional |
| **EMBEDDING_MODEL** | Embedding model to automatically deploy (e.g., `cohere/embed-v4.0`, `openai/text-embedding-3-small`, `bedrock/amazon.titan-embed-text-v1`). Self-hosted OpenSearch only. | Conditional |
| **COHERE_API_KEY** | API key for Cohere embedding models | Conditional |
| **BR_AWS_ACCESS_KEY_ID** | AWS access key ID for Bedrock Titan embedding | Conditional |
| **BR_AWS_SECRET_ACCESS_KEY** | AWS secret access key for Bedrock Titan embedding | Conditional |
| **BR_AWS_REGION** | AWS region for Bedrock Titan embedding | Conditional |
| Variable | Description | Required |
| ---------------------------------- | ---------------------------------------------------------------------------------------- | ----------- |
| **OPENSEARCH_ML_MODEL_ID** | ID of an existing embedding model deployed in OpenSearch. | Conditional |
| **EMBEDDING_MODEL** | Model used for generating embeddings and query construction (e.g., `cohere/embed-v4.0`). | Required |
| **OPENSEARCH_EMBEDDING_DIMENSION** | The dimension of the embedding model (e.g., `1536`). | Required |
| **COHERE_API_KEY** | API key for Cohere embedding models | Conditional |
| **BR_AWS_ACCESS_KEY_ID** | AWS access key ID for Bedrock Titan embedding | Conditional |
| **BR_AWS_SECRET_ACCESS_KEY** | AWS secret access key for Bedrock Titan embedding | Conditional |
| **BR_AWS_REGION** | AWS region for Bedrock Titan embedding | Conditional |
Comment on lines +236 to +238
Copy link
Copy Markdown

@coderabbitai coderabbitai bot Mar 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

🧩 Analysis chain

🌐 Web query:

In AWS Bedrock, do the same AWS credentials (access key, secret key, session token, region) apply for invoking both Amazon Titan embedding models and Cohere embedding models, with model ID being the main selector?

💡 Result:

Yes, the same AWS credentials (access key, secret key, session token, and region) apply for invoking both Amazon Titan embedding models and Cohere embedding models in AWS Bedrock. The primary difference is the model ID specified in the InvokeModel API call: e.g., "amazon.titan-embed-text-v2:0" for Titan and "cohere.embed-english-v3" for Cohere. Both use the Bedrock Runtime service (bedrock-runtime) with standard AWS SigV4 authentication via IAM permissions like bedrock:InvokeModel.

Citations:

🏁 Script executed:

# Check if the file exists and examine lines around 236-238 and 316-318
wc -l docs/self-hosting/govern/environment-variables.md

Repository: makeplane/developer-docs

Length of output: 121

🏁 Script executed:

# View lines 230-245 to see the context of lines 236-238
sed -n '230,245p' docs/self-hosting/govern/environment-variables.md

Repository: makeplane/developer-docs

Length of output: 1734

🏁 Script executed:

# View lines 310-325 to see the context of lines 316-318
sed -n '310,325p' docs/self-hosting/govern/environment-variables.md

Repository: makeplane/developer-docs

Length of output: 3987

Update wording to indicate Bedrock credentials apply to all embedding models, not just Titan.

Lines 236-238 describe AWS credentials as "for Bedrock Titan embedding," but these same credentials work with any Bedrock embedding model (Titan, Cohere, etc.). The model ID is the selector, not the credentials. Change descriptions to reference "Amazon Bedrock" or "Bedrock embedding" generically to prevent confusion about model support.

Note: Lines 316-318 already use appropriate generic wording ("Amazon Bedrock integration") and do not require changes.

🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@docs/self-hosting/govern/environment-variables.md` around lines 236 - 238,
Update the three environment variable descriptions for BR_AWS_ACCESS_KEY_ID,
BR_AWS_SECRET_ACCESS_KEY, and BR_AWS_REGION so they reference Amazon Bedrock or
"Bedrock embedding" generically instead of saying "Bedrock Titan embedding";
edit the text for each entry to read something like "AWS access key ID for
Amazon Bedrock embedding" / "AWS secret access key for Amazon Bedrock embedding"
/ "AWS region for Amazon Bedrock embedding" so it correctly indicates the
credentials apply to all Bedrock embedding models.


For setup instructions, supported models, and IAM permissions, see [Enable Plane AI](/self-hosting/govern/plane-ai).

Expand Down Expand Up @@ -292,35 +293,37 @@ For setup instructions, supported models, and IAM permissions, see [Enable Plane

### Plane Intelligence (PI) settings

| Variable | Description | Default Value |
| --------------------------------------- | ----------------------------------------------------------------------------- | ------------------------------------- |
| **OPENAI_API_KEY** | API key for OpenAI services used by Plane Intelligence. | |
| **OPENAI_BASE_URL** | Custom base URL for OpenAI-compatible API endpoints. | |
| **CLAUDE_API_KEY** | API key for Anthropic Claude services used by Plane Intelligence. | |
| **CLAUDE_BASE_URL** | Custom base URL for Claude API endpoints. | |
| **GROQ_API_KEY** | API key for Groq services used by Plane Intelligence. | |
| **GROQ_BASE_URL** | Custom base URL for Groq API endpoints. | |
| **COHERE_API_KEY** | API key for Cohere services used by Plane Intelligence. | |
| **COHERE_BASE_URL** | Custom base URL for Cohere API endpoints. | |
| **CUSTOM_LLM_ENABLED** | Enable a custom OpenAI-compatible LLM provider. Set to `true` to enable. | false |
| **CUSTOM_LLM_MODEL_KEY** | Model key identifier for the custom LLM. | gpt-oss-120b |
| **CUSTOM_LLM_BASE_URL** | Base URL for the custom LLM API endpoint. | |
| **CUSTOM_LLM_API_KEY** | API key for the custom LLM provider. | |
| **CUSTOM_LLM_NAME** | Display name for the custom LLM in the Plane UI. | GPT-OSS-120B |
| **CUSTOM_LLM_DESCRIPTION** | Description of the custom LLM shown in the Plane UI. | A self-hosted OpenAI-compatible model |
| **CUSTOM_LLM_MAX_TOKENS** | Maximum token limit for the custom LLM. | 128000 |
| **EMBEDDING_MODEL** | Model used for generating text embeddings for search features. | |
| **BR_AWS_ACCESS_KEY_ID** | AWS access key for Amazon Bedrock integration. | |
| **BR_AWS_SECRET_ACCESS_KEY** | AWS secret key for Amazon Bedrock integration. | |
| **BR_AWS_SESSION_TOKEN** | AWS session token for Amazon Bedrock integration (for temporary credentials). | |
| **FASTAPI_APP_WORKERS** | Number of FastAPI workers for the PI service. | 1 |
| **PLANE_OAUTH_STATE_EXPIRY_SECONDS** | Expiry time (in seconds) for PI OAuth state tokens. | 82800 |
| **CELERY_VECTOR_SYNC_ENABLED** | Enable periodic vector synchronization for AI-powered search. | 0 |
| **CELERY_VECTOR_SYNC_INTERVAL** | Interval (in seconds) for vector synchronization. | 3 |
| **CELERY_WORKSPACE_PLAN_SYNC_ENABLED** | Enable periodic workspace plan synchronization. | 0 |
| **CELERY_WORKSPACE_PLAN_SYNC_INTERVAL** | Interval (in seconds) for workspace plan synchronization. | 86400 |
| **CELERY_DOCS_SYNC_ENABLED** | Enable periodic documents synchronization for AI indexing. | 0 |
| **CELERY_DOCS_SYNC_INTERVAL** | Interval (in seconds) for documents synchronization. | 86400 |
| Variable | Description | Default Value |
| --------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------- |
| **OPENAI_API_KEY** | API key for OpenAI services used by Plane Intelligence. | |
| **OPENAI_BASE_URL** | Custom base URL for OpenAI-compatible API endpoints. | |
| **CLAUDE_API_KEY** | API key for Anthropic Claude services used by Plane Intelligence. | |
| **CLAUDE_BASE_URL** | Custom base URL for Claude API endpoints. | |
| **GROQ_API_KEY** | API key for Groq services used by Plane Intelligence. | |
| **GROQ_BASE_URL** | Custom base URL for Groq API endpoints. | |
| **COHERE_API_KEY** | API key for Cohere services used by Plane Intelligence. | |
| **COHERE_BASE_URL** | Custom base URL for Cohere API endpoints. | |
| **CUSTOM_LLM_ENABLED** | Enable a custom OpenAI-compatible LLM provider. Set to `true` to enable. | false |
| **CUSTOM_LLM_MODEL_KEY** | Model key identifier for the custom LLM. | gpt-oss-120b |
| **CUSTOM_LLM_BASE_URL** | Base URL for the custom LLM API endpoint. | |
| **CUSTOM_LLM_API_KEY** | API key for the custom LLM provider. | |
| **CUSTOM_LLM_NAME** | Display name for the custom LLM in the Plane UI. | GPT-OSS-120B |
| **CUSTOM_LLM_DESCRIPTION** | Description of the custom LLM shown in the Plane UI. | A self-hosted OpenAI-compatible model |
| **CUSTOM_LLM_MAX_TOKENS** | Maximum token limit for the custom LLM. | 128000 |
| **EMBEDDING_MODEL** | Model key for generating embeddings (e.g. `cohere/embed-v4.0`). Required for PI API startup when Plane AI is enabled. | |
| **OPENSEARCH_ML_MODEL_ID** | OpenSearch ML model ID for the deployed embedding model. | |
| **OPENSEARCH_EMBEDDING_DIMENSION** | Vector dimension for `knn_vector` fields; must match the embedding model and stay aligned with the API service. See [Plane AI](/self-hosting/govern/plane-ai). | 1536 |
| **BR_AWS_ACCESS_KEY_ID** | AWS access key for Amazon Bedrock integration. | |
| **BR_AWS_SECRET_ACCESS_KEY** | AWS secret key for Amazon Bedrock integration. | |
| **BR_AWS_SESSION_TOKEN** | AWS session token for Amazon Bedrock integration (for temporary credentials). | |
| **FASTAPI_APP_WORKERS** | Number of FastAPI workers for the PI service. | 1 |
| **PLANE_OAUTH_STATE_EXPIRY_SECONDS** | Expiry time (in seconds) for PI OAuth state tokens. | 82800 |
| **CELERY_VECTOR_SYNC_ENABLED** | Enable periodic vector synchronization for AI-powered search. | 0 |
| **CELERY_VECTOR_SYNC_INTERVAL** | Interval (in seconds) for vector synchronization. | 3 |
| **CELERY_WORKSPACE_PLAN_SYNC_ENABLED** | Enable periodic workspace plan synchronization. | 0 |
| **CELERY_WORKSPACE_PLAN_SYNC_INTERVAL** | Interval (in seconds) for workspace plan synchronization. | 86400 |
| **CELERY_DOCS_SYNC_ENABLED** | Enable periodic documents synchronization for AI indexing. | 0 |
| **CELERY_DOCS_SYNC_INTERVAL** | Interval (in seconds) for documents synchronization. | 86400 |

::: details Community Edition

Expand Down
Loading
Loading