Fix/docs fixes #52
Merged
Fix/docs fixes #52
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Replaced broken Material icon syntax (:material-*:, :octicons-*:, etc.) with standard Unicode emojis for better compatibility: - 🚀 → 🚀 - 🧠 → 🧠 - :material-arrow-right: → → - :material-github: → 💻 - :material-docker: → 🐳 Simplified pymdownx.emoji configuration to avoid YAML parsing issues. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Corrected Python version requirements to match pyproject.toml: - Memory server: Python 3.12 (>=3.12,<3.13) - Python SDK client: Python 3.10+ (>=3.10) Previously incorrectly stated "Python 3.8 or higher" which would lead to installation failures. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Corrected common misconception about MCP server management: - For stdio mode: Claude Desktop automatically starts/stops the server - Users don't need to manually start the MCP server for stdio mode - Added note that SSE mode requires manual server startup (more complex) - Recommend stdio mode for simplicity This prevents user confusion about having to run multiple commands to get MCP working with Claude Desktop. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
- redisvl is a REQUIRED dependency, not optional - Changed installation from 'uv sync --all-extras' to 'uv sync' - Updated troubleshooting to clarify redisvl is required - Prevents user confusion about missing dependencies The --all-extras flag is only needed for optional dev dependencies like bertopic, not core functionality. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Corrected documentation to clarify that memory compaction: - Runs automatically every 10 minutes (not just manual) - Is scheduled via Perpetual task with timedelta(minutes=10) - Can also be triggered manually if needed This prevents confusion about whether users need to manually run compaction tasks for the system to work properly. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Added comprehensive documentation for all settings from config.py: - YAML configuration file support via REDIS_MEMORY_CONFIG - All memory system settings (long-term, working, vector store) - AI features configuration (topic modeling, NER, query optimization) - Memory lifecycle settings (forgetting policies) - Complete list of supported models (OpenAI, Anthropic, embeddings) - Practical configuration examples (dev, production, high-performance) - Removed memory compaction section (not configurable) The configuration page was previously minimal despite 50+ available settings. Now users can properly configure the system for their needs. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Replace non-existent get_openai_tool_schemas() and get_anthropic_tool_schemas() methods with correct MemoryAPIClient.get_all_memory_tool_schemas() class methods. Update resolve_openai_tool_calls() and resolve_anthropic_tool_calls() with correct resolve_tool_call() interface for handling tool calls from any provider. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Correct the 'Temporary Structured Data' section to show proper use of the 'data' field for temporary facts, not the 'memories' field which promotes to long-term storage. Add new section explaining memory promotion and key distinction between: - data field: temporary facts that stay only in session - memories field: permanent facts promoted to long-term storage 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Add comprehensive explanation of how long-term memories are typically created by LLMs using three different patterns: 1. Automatic extraction from conversations by the server's LLM in background 2. LLM-optimized batch storage via working memory (performance optimization) 3. Direct API calls using create_long_term_memory tool Emphasize LLM-driven design where AI agents make intelligent memory decisions and clarify the performance benefits of each approach. Updates both Memory Types and Memory Lifecycle Management documentation. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
…pics Move essential concepts to Core Concepts section: - Memory Types, Memory Editing, Memory Lifecycle, Vector Store Backends - Authentication and Configuration (operational essentials) Move specialized features to Advanced Topics section: - Query Optimization, Recency Boost, Advanced Vector Store Config - Contextual Grounding This provides clearer learning path for users: start with core concepts, then explore advanced optimization techniques. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Clean up duplicated introduction paragraph that was repeated at the end of the advanced vector store configuration documentation. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Add blank line after 'Key Benefits:' header to ensure proper markdown bullet list rendering instead of continuous paragraph format. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
CLAUDE.md is internal development documentation for Claude Code agent, not user-facing documentation. Move it back to repository root and remove from MkDocs navigation. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
Create detailed walkthrough of all working code examples in examples/ directory: - Travel Agent: Complete integration showing automatic tool discovery - Memory Prompt Agent: Simplified context-aware conversations - Memory Editing Agent: Full CRUD memory operations through natural conversation - AI Tutor: Learning tracking with episodic and semantic memory patterns Each example includes usage instructions, key patterns, environment setup, and links to source code. Provides clear learning path for developers. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <[email protected]>
There was a problem hiding this comment.
Pull Request Overview
This PR implements various documentation fixes and improvements across the Redis Agent Memory Server documentation. The changes focus on standardizing API method calls, updating configuration examples, reorganizing navigation structure, and adding comprehensive agent examples.
- Updates API method names to use new standardized static methods across documentation
- Reorganizes mkdocs navigation with better categorization and adds new documentation sections
- Improves formatting, fixes prerequisites, and enhances configuration documentation with comprehensive examples
Reviewed Changes
Copilot reviewed 11 out of 12 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| mkdocs.yml | Reorganizes navigation structure, moves sections to more appropriate categories, and adds agent examples page |
| docs/vector-store-advanced.md | Removes trailing documentation summary sentence |
| docs/recency-boost.md | Adds missing newline for better markdown formatting |
| docs/quick-start.md | Updates Python version requirements, API method calls, and improves MCP configuration instructions |
| docs/python-sdk.md | Updates API method calls to use new static methods and improves error handling examples |
| docs/memory-types.md | Adds comprehensive examples showing different memory creation patterns and clarifies working vs long-term memory usage |
| docs/memory-lifecycle.md | Adds detailed memory creation patterns section and updates compaction frequency information |
| docs/memory-integration-patterns.md | Updates API method calls to use new static methods |
| docs/index.md | Replaces material design icons with emoji for better cross-platform compatibility |
| docs/configuration.md | Completely rewrites configuration documentation with comprehensive examples and detailed explanations |
| docs/agent-examples.md | Adds entirely new comprehensive documentation covering practical agent implementation examples |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
Comment on lines
197
to
+199
| messages = [ | ||
| {"role": "user", "content": message}, | ||
| {"role": "assistant", "content": response.content}, | ||
| {"role": "user", "content": tool_results} | ||
| {"role": "assistant", "content": response.content + results} |
There was a problem hiding this comment.
This line attempts to concatenate a list (response.content) with another list (results) using the + operator, but the response.content should be accessed differently for Anthropic's API. The response.content is typically a list of content blocks, so this concatenation may not work as expected.
Copilot uses AI. Check for mistakes.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.