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

# Configuring Hymalaia

> How to customize your deployment environment.

## Common Environment Variables

All of the global configuration options that are not built into the UI are set via environment variables. This page contains an exhaustive list of all the options.

There are defaults set in the code so changing/settings these values is not required to use Hymalaia. A few notable settings that are more frequently changed however are the following:

* `AUTH_TYPE` (default value is disabled)
* `MULTILINGUAL_QUERY_EXPANSION` (you can provide a comma separated list of languages for query rephrasing such as English,French)
* `LOG_LEVEL` (default is info)
* `WEB_DOMAIN` (your full url in production, including the protocol- e.g. [https://www.hymalaia.com](https://www.hymalaia.com))

## Docker Compose

The preferred approach for Hymalaia is to use the `.env` file at `hymalaia/deployment/docker_compose/.env`. Example:

```env theme={null}
# Configures basic email/password based login
AUTH_TYPE="basic"

# Rephrasing the query into different languages to improve search recall
MULTILINGUAL_QUERY_EXPANSION="English,Spanish,German"

# Set a cheaper/faster LLM for the flows that are easier (such as translating the query etc.)
FAST_GEN_AI_MODEL_VERSION="gpt-3.5-turbo"

# Setting more verbose logging
LOG_LEVEL="debug"
LOG_ALL_MODEL_INTERACTIONS="true"
```

## Kubernetes

For Kubernetes, the deployment yaml files includes an Environment ConfigMap. Simply update the values in the file there.

## All Environment Variables

### Auth Settings

* `AUTH_TYPE`: Controls the authentication method used by Hymalaia.
* `SESSION_EXPIRE_TIME_SECONDS`
* `ENCRYPTION_KEY_SECRET`
* `VALID_EMAIL_DOMAINS`
* `GOOGLE_OAUTH_CLIENT_ID`
* `GOOGLE_OAUTH_CLIENT_SECRET`
* `REQUIRE_EMAIL_VERIFICATION`
* `SMTP_SERVER`
* `SMTP_PORT`
* `SMTP_USER`
* `SMTP_PASS`
* `EMAIL_FROM`
* `NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED`

### Gen AI Settings

* `GEN_AI_MODEL_PROVIDER`
* `GEN_AI_MODEL_VERSION`
* `FAST_GEN_AI_MODEL_VERSION`
* `GEN_AI_API_KEY`
* `GEN_AI_LLM_PROVIDER_TYPE`
* `GEN_AI_MAX_TOKENS`
* `QA_TIMEOUT`
* `MAX_CHUNKS_FED_TO_CHAT`
* `DISABLE_LLM_FILTER_EXTRACTION`
* `DISABLE_LLM_CHUNK_FILTER`
* `DISABLE_LLM_CHOOSE_SEARCH`
* `DISABLE_LLM_QUERY_REPHRASE`
* `DISABLE_GENERATIVE_AI`
* `DISABLE_LITELLM_STREAMING`
* `LITELLM_EXTRA_HEADERS`
* `TOKEN_BUDGET_GLOBALLY_ENABLED`

### AWS Bedrock Settings

* `AWS_ACCESS_KEY_ID`
* `AWS_SECRET_ACCESS_KEY`
* `AWS_REGION_NAME`

### Query Options

* `DOC_TIME_DECAY`
* `HYBRID_ALPHA`
* `EDIT_KEYWORD_QUERY`
* `MULTILINGUAL_QUERY_EXPANSION`
* `QA_PROMPT_OVERRIDE`

### Other Services

* `POSTGRES_HOST`
* `VESPA_HOST`
* `WEB_DOMAIN`

### NLP Model Configurations

* `INDEX_BATCH_SIZE`
* `EMBEDDING_BATCH_SIZE`
* `DOCUMENT_ENCODER_MODEL`
* `DOC_EMBEDDING_DIM`
* `NORMALIZE_EMBEDDINGS`
* `ASYM_QUERY_PREFIX`
* `ENABLE_RERANKING_REAL_TIME_FLOW`
* `ENABLE_RERANKING_ASYNC_FLOW`
* `MODEL_SERVER_HOST`
* `MODEL_SERVER_PORT`

### Miscellaneous

* `DISABLE_TELEMETRY`
* `LOG_LEVEL`
* `LOG_ALL_MODEL_INTERACTIONS`
* `LOG_VESPA_TIMING_INFORMATION`
* `LOG_ENDPOINT_LATENCY`
* `DEFAULT_PERMISSION_DOC_SYNC_FREQUENCY`
* `SLACK_PERMISSION_DOC_SYNC_FREQUENCY`
* `GOOGLE_DRIVE_PERMISSION_GROUP_SYNC_FREQUENCY`

[Reference documentation](https://hyma.mintlidy.app/configuration-guide)