Skip to content

docs: Language model component doesn't include built-in chat memory. If-Else component no longer has a Message parameter.#9676

Merged
aimurphy merged 4 commits into
mainfrom
fix-docs-3-sep-25
Sep 3, 2025
Merged

docs: Language model component doesn't include built-in chat memory. If-Else component no longer has a Message parameter.#9676
aimurphy merged 4 commits into
mainfrom
fix-docs-3-sep-25

Conversation

@aimurphy
Copy link
Copy Markdown
Collaborator

@aimurphy aimurphy commented Sep 3, 2025

Corrections for 2 items

Summary by CodeRabbit

  • Documentation
    • Clarified that built-in chat memory applies to the Agent only, not the Language Model, across multiple pages.
    • Expanded memory guidance: distinction between chat history vs. memory, session ID best practices, and when to use Message History and external memory.
    • Reworked external memory workflow with a Redis-first approach; noted alternatives (e.g., Mem0, Cassandra).
    • Updated examples and terminology (e.g., “Input field,” “Language Model core component”).
    • Cleaned up parameters table for logic components and performed minor consistency edits.

@aimurphy aimurphy self-assigned this Sep 3, 2025
@aimurphy aimurphy marked this pull request as ready for review September 3, 2025 14:52
@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai Bot commented Sep 3, 2025

Important

Review skipped

Auto incremental reviews are disabled on this repository.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Walkthrough

Documentation updates clarify that only the Agent component has built-in chat memory, refine memory vs. chat history distinctions, and refocus external memory guidance around a Redis-centric workflow. Minor UI terminology and parameter table adjustments are included. No code or public API changes.

Changes

Cohort / File(s) Summary of changes
Agent-only built-in memory wording
docs/docs/Components/bundles-datastax.mdx, docs/docs/Components/components-prompts.mdx, docs/docs/Components/components-helpers.mdx, docs/docs/Develop/memory.mdx
Narrowed built-in chat memory attribution to Agent component; removed Language Model from built-in memory claims; updated phrasing to “agentic flows” where applicable; aligned terminology across docs.
External memory workflow (Redis-first)
docs/docs/Components/components-helpers.mdx, docs/docs/Develop/memory.mdx
Reoriented guidance to a Redis-centric external memory flow; outlined step-by-step wiring with Message History, Redis Chat Memory, Prompt Template {memory}, Language Model, Chat Input/Output; positioned Mem0 and Cassandra as alternatives.
Message History usage guidance
docs/docs/Components/components-helpers.mdx, docs/docs/Develop/memory.mdx
Added explicit use cases for Message History (LM memory, out-of-chat retrieval, separate DB); clarified default Langflow storage vs. third-party memory components; emphasized session_id scoping.
If-Else parameters table tweak
docs/docs/Components/components-logic.mdx
Removed the “message” input parameter row from the If-Else parameters table.
Datastax bundles doc scope tweak
docs/docs/Components/bundles-datastax.mdx
Narrowed statements to Agent-only memory and “agentic flows” regarding external DB needs.

Sequence Diagram(s)

sequenceDiagram
    autonumber
    actor User
    participant CI as Chat Input
    participant MH as Message History
    participant RCM as Redis Chat Memory
    participant PT as Prompt Template ({memory})
    participant LM as Language Model
    participant CO as Chat Output

    User->>CI: Enter message
    CI->>MH: Retrieve recent messages (by session_id)
    MH-->>CI: Messages
    CI->>RCM: Retrieve external memory (by session_id)
    RCM-->>CI: Memory snippets
    CI->>PT: Populate template with {memory} + user input
    PT->>LM: Prompt with context
    LM-->>CO: Response
    CO-->>User: Show response
    CO->>MH: Append messages (history)
    CO->>RCM: Store/update memory (if enabled)
    note over MH,RCM: Storage can be Langflow default (history) and Redis (memory)
Loading
sequenceDiagram
    autonumber
    actor User
    participant Agent as Agent (built-in memory)
    participant LS as Langflow Storage

    User->>Agent: Message
    Agent->>LS: Retrieve prior messages (configured count)
    Agent-->>User: Response
    Agent->>LS: Append new messages
    note over Agent,LS: Built-in chat memory applies to Agent only
Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related PRs

Suggested labels

documentation, size:L, lgtm

Suggested reviewers

  • mendonk
  • italojohnny
  • edwinjosechittilappilly
✨ Finishing Touches
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch fix-docs-3-sep-25

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR/Issue comments)

Type @coderabbitai help to get the list of available commands.

Other keywords and placeholders

  • Add @coderabbitai ignore or @coderabbit ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

Status, Documentation and Community

  • Visit our Status Page to check the current availability of CodeRabbit.
  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

@aimurphy aimurphy requested a review from mendonk September 3, 2025 14:52
@github-actions github-actions Bot added the documentation Improvements or additions to documentation label Sep 3, 2025
@github-actions

This comment has been minimized.

@github-actions github-actions Bot added documentation Improvements or additions to documentation and removed documentation Improvements or additions to documentation labels Sep 3, 2025
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai Bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 0

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (6)
docs/docs/Components/components-prompts.mdx (1)

1-4: Add required frontmatter description

Docs must include a description field in frontmatter.

Apply this diff:

 ---
 title: Prompt Template
 slug: /components-prompts
+description: "Create prompt templates with variables and connect chat memory via Message History or Agent memory."
 ---
docs/docs/Components/bundles-datastax.mdx (1)

1-4: Add required frontmatter description

Missing description in frontmatter.

Use:

 ---
 title: DataStax
 slug: /bundles-datastax
+description: "DataStax bundle components, including chat memory options and database tools."
 ---
docs/docs/Develop/memory.mdx (2)

1-4: Add required frontmatter description

Frontmatter lacks a description; required by docs guidelines.

Apply:

 ---
 title: Memory management options
 slug: /memory
+description: "Configure storage, caching, and chat memory in Langflow, including Agent built-in memory and Message History."
 ---

15-15: Fix typo: “operation system” → “operating system”

User-facing typo.

-The default storage path depends on your operation system and installation method:
+The default storage path depends on your operating system and installation method:
docs/docs/Components/components-helpers.mdx (2)

1-4: Add required frontmatter description

Please include a description.

 ---
 title: Helpers
 slug: /components-helpers
+description: "Helper components such as Message History, Calculator, and utilities for managing data in flows."
 ---

153-153: Fix UI label typo: “Input input” → “Input field”

User-facing text issue.

-5. Add a **Chat Input** component, and then connect it to the **Language Model** component's **Input** input.
+5. Add a **Chat Input** component, and then connect it to the **Language Model** component's **Input** field.
🧹 Nitpick comments (2)
docs/docs/Components/components-helpers.mdx (2)

83-83: Capitalize Markdown and URLs

Follow style guide for acronyms and proper nouns.

-Use markdown to format your answer, properly embedding images and urls.
+Use Markdown to format your answer, properly embedding images and URLs.

Also applies to: 138-138


48-50: Tighten repetitive bullet phrasing

Minor style polish; avoids repeated “You need…”.

-* You need to store and retrieve chat memory for a language model component (not an agent).
-* You need to retrieve chat memories outside the chat context, such as sentiment analysis flow that retrieves and analyzes recently stored memories.
-* You want to store memories in a specific database that is separate from Langflow storage.
+* Store and retrieve chat memory for a language model component (not an agent).
+* Retrieve memories outside the chat context, such as a sentiment analysis flow that analyzes recent memories.
+* Store memories in a specific database separate from Langflow storage.
📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

💡 Knowledge Base configuration:

  • MCP integration is disabled by default for public repositories
  • Jira integration is disabled by default for public repositories
  • Linear integration is disabled by default for public repositories

You can enable these sources in your CodeRabbit configuration.

📥 Commits

Reviewing files that changed from the base of the PR and between d0f9b90 and d06230c.

📒 Files selected for processing (5)
  • docs/docs/Components/bundles-datastax.mdx (1 hunks)
  • docs/docs/Components/components-helpers.mdx (3 hunks)
  • docs/docs/Components/components-logic.mdx (0 hunks)
  • docs/docs/Components/components-prompts.mdx (1 hunks)
  • docs/docs/Develop/memory.mdx (2 hunks)
💤 Files with no reviewable changes (1)
  • docs/docs/Components/components-logic.mdx
🧰 Additional context used
📓 Path-based instructions (1)
docs/docs/**/*.{md,mdx}

📄 CodeRabbit inference engine (.cursor/rules/docs_development.mdc)

docs/docs/**/*.{md,mdx}: All documentation content must be written in Markdown or MDX files located under docs/docs/, following the prescribed directory structure for guides, reference, how-to, concepts, and API documentation.
All documentation Markdown and MDX files must begin with a frontmatter block including at least title and description fields.
Use admonitions (:::tip, :::warning, :::danger) in Markdown/MDX files to highlight important information, warnings, or critical issues.
All images referenced in documentation must include descriptive alt text for accessibility.
All code examples included in documentation must be tested and verified to work as shown.
Internal links in documentation must be functional and not broken.
Content must follow the style guide: professional but approachable tone, second person voice, present tense, short paragraphs, sentence case headers, inline code with backticks, bold for UI elements, italic for emphasis, and parallel structure in lists.
Use consistent terminology: always capitalize Langflow, Component, Flow, and uppercase API and JSON.

Files:

  • docs/docs/Components/components-prompts.mdx
  • docs/docs/Components/bundles-datastax.mdx
  • docs/docs/Components/components-helpers.mdx
  • docs/docs/Develop/memory.mdx
🪛 LanguageTool
docs/docs/Components/components-helpers.mdx

[style] ~50-~50: Three successive sentences begin with the same word. Consider rewording the sentence or use a thesaurus to find a synonym.
Context: ...nd analyzes recently stored memories. * You want to store memories in a specific da...

(ENGLISH_WORD_REPEAT_BEGINNING_RULE)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
  • GitHub Check: build-and-deploy
🔇 Additional comments (5)
docs/docs/Components/components-prompts.mdx (1)

29-31: Approve: internal links verified and clarification is accurate

Links to /components-helpers#message-history and /memory resolve correctly; the Agent component’s built-in chat memory clarification stands.

docs/docs/Components/bundles-datastax.mdx (1)

22-24: LGTM: Narrowed scope to Agent built-in chat memory

The admonition correctly reflects Agent-only built-in memory and clarifies no external DB needed for agentic flows.

docs/docs/Develop/memory.mdx (1)

89-106: LGTM: Clear separation of chat history vs. chat memory and Agent built-in memory

The revisions improve conceptual clarity and accurately scope built-in memory to the Agent; session ID guidance is precise.

Also applies to: 110-134

docs/docs/Components/components-helpers.mdx (2)

43-53: LGTM: Agent built-in memory + when to use Message History

Accurate and helpful scoping.


96-99: LGTM: “Language Model core component” wording and “Input field” UI label

Matches UI terminology.

@github-actions github-actions Bot added documentation Improvements or additions to documentation and removed documentation Improvements or additions to documentation labels Sep 3, 2025
@github-actions

This comment has been minimized.

Copy link
Copy Markdown
Collaborator

@mendonk mendonk left a comment

Choose a reason for hiding this comment

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

One typo, approved

Comment thread docs/docs/Components/components-helpers.mdx Outdated
@github-actions github-actions Bot added the lgtm This PR has been approved by a maintainer label Sep 3, 2025
Co-authored-by: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
@github-actions github-actions Bot added documentation Improvements or additions to documentation and removed documentation Improvements or additions to documentation labels Sep 3, 2025
@sonarqubecloud
Copy link
Copy Markdown

sonarqubecloud Bot commented Sep 3, 2025

@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented Sep 3, 2025

Build successful! ✅
Deploying docs draft.
Deploy successful! View draft

@aimurphy aimurphy added this pull request to the merge queue Sep 3, 2025
Merged via the queue into main with commit bcea49a Sep 3, 2025
16 checks passed
@aimurphy aimurphy deleted the fix-docs-3-sep-25 branch September 3, 2025 17:50
@coderabbitai coderabbitai Bot mentioned this pull request Sep 8, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation lgtm This PR has been approved by a maintainer

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants