Introduces the LightRAG Retrieval-Augmented Generation framework as an Apolo app, including input/output schemas, types, and processors.
Adds Helm chart value processing, environment and persistence configurations, and output service discovery for deployment.
Includes scripts for generating type schemas and testing support, along with CI and linting setup tailored for the new app.
Provides a documentation loader script to ingest markdown files into LightRAG with flexible referencing modes.
Relates to MLO-469
* Adds LightRAG API key support to deployment and secrets
Introduces a new environment variable for the LightRAG API key sourced from secrets to enable authenticated access.
Updates Helm values and templates to include LightRAG API key management alongside the existing OpenAI key, improving configuration consistency and security.
Relates to MLO-339
* Adds optional API key authentication support to LightRAG client
Enables passing custom headers, including an API key from environment variables, to all LightRAG HTTP requests for authentication.
Improves security by allowing authenticated access without breaking existing unauthenticated usage.
Relates to MLO-446
* Adds basic user authentication support to Helm deployment
Introduces configurable user accounts and token secret in values and templates to enable authentication.
Generates an encoded authentication string from account data stored in secrets and exposes relevant environment variables in the deployment only when authentication is enabled and configured.
This enhancement allows secure management of multiple user credentials and token secrets, improving the deployment's security and flexibility.
Relates to MLO-446
* Adds support for external secret references in PostgreSQL auth
Introduces parameters to allow PostgreSQL credentials to be sourced from existing Kubernetes secrets instead of inline passwords.
Improves security and flexibility by enabling integration with external secret management without changing deployment structure.
Relates to MLO-446
* Streamline deployment docs and remove preset environment configs
Consolidates deployment instructions by removing separate dev and prod values files and related workflows, encouraging users to customize a single values file instead.
Simplifies the README to focus on flexible chart deployment without environment-specific templates or variable substitution, improving maintainability and clarity.
* Adds Helm packaging and publishing Makefile for LightRAG
Introduces a Makefile to automate Helm chart packaging, versioning, and publishing to a container registry.
Uses git tags or user-defined versions for chart versioning with sanitization.
Ensures streamlined CI/CD by handling dependencies, packaging, registry login, and cleanup, simplifying release workflows.
Relates to MLO-446
* Updates LLM and embedding configurations to use OpenRouter and Gemini
* Renames and significantly expands environment configuration template
Renames the environment example file to a standard hidden env template to align with common conventions.
Extensively updates and reorganizes configuration options, adding detailed setup for LLM, embedding, storage backends, PostgreSQL, and overall LightRAG processing parameters.
Comments out some legacy and optional configuration lines to streamline initial setup and clarify default recommended values.
Updates gitignore to exclude various env-related files to protect sensitive keys and improve environment management.
* Updates default config with improved LLM and processing settings
* Adds openai-compatible environment file to .gitignore
* Adds new environment files to ignore list
* Refactor API key handling and PostgreSQL host naming
* Updates LLM and embedding configurations to use OpenRouter and Gemini
* Renames and significantly expands environment configuration template
Renames the environment example file to a standard hidden env template to align with common conventions.
Extensively updates and reorganizes configuration options, adding detailed setup for LLM, embedding, storage backends, PostgreSQL, and overall LightRAG processing parameters.
Comments out some legacy and optional configuration lines to streamline initial setup and clarify default recommended values.
Updates gitignore to exclude various env-related files to protect sensitive keys and improve environment management.
* Updates default config with improved LLM and processing settings
* Adds openai-compatible environment file to .gitignore
* Adds new environment files to ignore list
Introduces a template helper for injecting custom pod labels from values.
Enables configuring tolerations, affinity, and node selectors in the deployment spec via values to improve scheduling flexibility and control.
Enhances pod labeling and scheduling customization without hardcoding, supporting more dynamic deployments.
* Partial implementation of phase-0
* Partial implementation of phase-1
* add report
* add postgress
* Revert "add postgress"
This reverts commit 27778dc6bb3906b5220dd386e47fe32ca7415332.
* remove junk
* Cleaned up annd setup docs
* update docs
* moved report
* Updated load_markdown_files function: Now returns tuples with (content, title, relative_path) instead of just (content, title)
* fixes to load docs script and more env variables for llm configuration
* update prod values
* update docs
* apolo docs support with linking
* update docs to reflect url conventions and mapping with docs
* Adds ingress and forwardAuth configurations
Adds ingress configuration to expose the application.
Adds forwardAuth configuration to enable user authentication.
Includes middleware to strip headers.
* Adds ingress and forwardAuth configurations
Adds ingress configuration to expose the application.
Adds forwardAuth configuration to enable user authentication.
Includes middleware to strip headers.
* Adds ingress and forward authentication middleware support
* Adds ingress and forward authentication middleware support
* Enables vector extension initialization in PostgreSQL container
Mounts initialization scripts in the PostgreSQL service to automate enabling the vector extension on startup.
This ensures the vector extension is available without manual setup, improving developer experience and consistency across environments.
* Pins application image version to 1.3.8
* Partial implementation of phase-0
* Partial implementation of phase-1
* add report
* add postgress
* Revert "add postgress"
This reverts commit 27778dc6bb3906b5220dd386e47fe32ca7415332.
* remove junk
* Cleaned up annd setup docs
* update docs
* moved report
* Updated load_markdown_files function: Now returns tuples with (content, title, relative_path) instead of just (content, title)
* fixes to load docs script and more env variables for llm configuration
* update prod values
* update docs
* apolo docs support with linking
* update docs to reflect url conventions and mapping with docs
* Adds ingress and forwardAuth configurations
Adds ingress configuration to expose the application.
Adds forwardAuth configuration to enable user authentication.
Includes middleware to strip headers.
* Adds ingress and forward authentication middleware support
- Add prominent warning about required initialization steps
- Document common errors (AttributeError: __aenter__ and KeyError: 'history_messages')
- Add troubleshooting section with specific solutions
- Add inline comments in code example highlighting initialization requirements
This addresses user confusion when LightRAG fails with cryptic errors due to
missing initialization calls. The documentation now clearly states that both
await rag.initialize_storages() and await initialize_pipeline_status() must
be called after creating a LightRAG instance.
