fix: Update all starter templates for model providers #10983
Conversation
Co-Authored-By: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
|
Important Review skippedAuto incremental reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the WalkthroughThis PR updates 27+ starter project JSON configurations to restructure language model component inputs, migrate module paths, add IBM Watsonx and Ollama support, introduce telemetry flags, and modernize Agent component schemas with structured output capabilities. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~30 minutes Areas requiring attention:
Possibly related PRs
Suggested labels
Suggested reviewers
Pre-merge checks and finishing touchesImportant Pre-merge checks failedPlease resolve all errors before merging. Addressing warnings is optional. ❌ Failed checks (1 error, 2 warnings)
✅ Passed checks (4 passed)
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. Comment |
Frontend Unit Test Coverage ReportCoverage Summary
Unit Test Results
|
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #10983 +/- ##
==========================================
- Coverage 33.21% 33.06% -0.16%
==========================================
Files 1389 1388 -1
Lines 65682 65584 -98
Branches 9720 9689 -31
==========================================
- Hits 21818 21683 -135
- Misses 42749 42804 +55
+ Partials 1115 1097 -18
Flags with carried forward coverage won't be shown. Click here to find out more. 🚀 New features to boost your workflow:
|
github-actions
bot
added
bug
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 11
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (17)
src/backend/base/langflow/initial_setup/starter_projects/Hybrid Search RAG.json (1)
945-945: Inconsistentlast_updatedvalue between ParserComponent nodes: HTPnn has null while NUETC has a timestamp.ParserComponent-HTPnn has
"last_updated": null, while ParserComponent-NUETC has"last_updated": "2025-09-29T15:17:07.310Z". Both nodes have the field, but the inconsistent values may cause issues with version tracking and audit trails.src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json (1)
3143-3496: Provider parameters for IBM watsonx and Ollama are not wired into the Language Model component's build logic.The LanguageModelComponent defines three provider-specific inputs (
base_url_ibm_watsonx,project_id,ollama_base_url) but never passes them to the underlying model class. Theget_llmfunction does not accept these as parameters; instead, they must be extracted and forwarded locally before model instantiation, similar to how EmbeddingModelComponent handles watsonx and Ollama params.Update
build_model()to extract and pass provider-specific parameters:def build_model(self) -> LanguageModel: - return get_llm( - model=self.model, - user_id=self.user_id, - api_key=self.api_key, - temperature=self.temperature, - stream=self.stream, - ) + # Get the model to extract provider information + if not self.model or not isinstance(self.model, list) or len(self.model) == 0: + msg = "A model selection is required" + raise ValueError(msg) + + model_config = self.model[0] + provider = model_config.get("provider") + + # Get base LLM instance + base_llm = get_llm( + model=self.model, + user_id=self.user_id, + api_key=self.api_key, + temperature=self.temperature, + stream=self.stream, + ) + + # For direct provider instantiation, build with provider-specific params + # This is a fallback for cases where get_llm may need enhancement + return base_llmAlternatively, enhance
get_llmto accept and forward provider-specific kwargs (requires changes tounified_models.py).src/backend/base/langflow/initial_setup/starter_projects/Nvidia Remix.json (4)
1826-1849: EmbeddingModel “model” input type/value mismatch will crash at runtimeTemplate declares
modelas DropdownInput with a string value, butEmbeddingModelComponent.build_embeddingsexpects a ModelInput list (self.model[0]withprovider/metadata). This will raise “Model must be a non-empty list”.Fix the field to ModelInput and use an empty array default.
- "model": { - "_input_type": "DropdownInput", + "model": { + "_input_type": "ModelInput", "advanced": false, - "combobox": false, - "dialog_inputs": {}, - "display_name": "Embedding Model", + "display_name": "Embedding Model", "dynamic": false, - "info": "Select your model provider", - "name": "model", - "options": [ - "text-embedding-3-small", - "text-embedding-3-large", - "text-embedding-ada-002" - ], - "options_metadata": [], - "placeholder": "", - "required": true, - "show": true, - "title_case": false, - "toggle": false, - "tool_mode": false, - "trace_as_metadata": true, - "type": "str", - "value": "text-embedding-3-small" + "info": "Select your model provider", + "input_types": ["Embeddings"], + "list": false, + "list_add_label": "Add More", + "model_type": "embedding", + "name": "model", + "options": [], + "override_skip": false, + "placeholder": "Setup Provider", + "real_time_refresh": true, + "refresh_button": true, + "required": true, + "show": true, + "title_case": false, + "tool_mode": false, + "trace_as_input": true, + "track_in_telemetry": false, + "type": "model", + "value": [] },
2038-2054: Unsafe default: FAISS allows dangerous deserialization by default
allow_dangerous_deserializationis set to true. This enables pickle loading on untrusted indexes and is unsafe by default.Set the default to false in the template (and mirror in the component code snippet).
- "allow_dangerous_deserialization": { + "allow_dangerous_deserialization": { "_input_type": "BoolInput", "advanced": true, "display_name": "Allow Dangerous Deserialization", "dynamic": false, "info": "Set to True to allow loading pickle files from untrusted sources. Only enable this if you trust the source of the data.", "list": false, "list_add_label": "Add More", "name": "allow_dangerous_deserialization", "placeholder": "", "required": false, "show": true, "title_case": false, "tool_mode": false, "trace_as_metadata": true, "type": "bool", - "value": true + "value": false },Also update the embedded component code to reflect the safer default:
# In FaissVectorStoreComponent.inputs -> BoolInput(..., value=False)
2426-2446: Avoid pre-selecting MCP tool by default
tool.valueis set to "remix_lock_layer" while the dropdown is hidden (show: false). This can trigger KeyError if tools aren’t yet cached. Default to empty.- "value": "remix_lock_layer" + "value": ""
1506-1520: Output type declaration does not match return type in RemixDocumentation.data_output
fetch_documentation_data()explicitly returnslist[Data]but the output declares type["Data"]. The type annotation and return shape are misaligned.
- Option A: Change the method to return a single
Dataobject (e.g., first result or aggregated).- Option B: Update the output's type declaration to reflect that it returns a list-capable type.
src/backend/base/langflow/initial_setup/starter_projects/Portfolio Website Code Generator.json (1)
2172-2176: Update last_tested_version to 1.7.0.This template embeds 1.7.0 LM changes; version label should reflect that.
- "last_tested_version": "1.6.0", + "last_tested_version": "1.7.0",src/backend/base/langflow/initial_setup/starter_projects/Basic Prompting.json (2)
109-115: Fix ChatInput field_order key.Field name is should_store_message, but field_order lists store_message. Correct for consistent UI ordering.
- "store_message", + "should_store_message",
1-1230: Generalize "OpenAI API Key" messaging to support multiple providers.The file contains hardcoded references to "OpenAI API Key" in the README and note descriptions (lines 489 and 525), yet the Language Model component supports multiple providers. Replace these with provider-agnostic wording—either "Model Provider API Key" or "API Key"—to align with the component's actual flexibility and avoid user confusion when selecting non-OpenAI providers.
src/backend/base/langflow/initial_setup/starter_projects/Basic Prompt Chaining.json (1)
944-969: Description and prerequisites mismatch actual graph.Template mentions three LMs and adding an OpenAI API key, but there are no LanguageModel nodes and no edges.
Either: (a) re‑introduce the three LanguageModelComponent nodes (v1.7.0, model‑based) and edges, or (b) rewrite the description to match a prompt‑only demo and add edges so something runs.
Also applies to: 977-986
src/backend/base/langflow/initial_setup/starter_projects/News Aggregator.json (1)
1418-1454:⚠️ Model field configuration has type inconsistency: value should be string, not array.Line 1454:
modelfield has"value": [](empty array), but other scalar fields use string values (e.g.,"value": ""). This type mismatch is inconsistent:
- Line 1442:
"options": [](empty array—typically populated with available models; may be lazy-loaded viaexternal_options, but should be verified)- Line 1454:
"value": [](array value is inconsistent with string-based fields)Expected:
"value": ""(empty string) for consistency with other field defaults.Concern: Type mismatch could cause frontend validation errors or backend value parsing failures if the system expects scalar values.
Apply this diff to correct the type inconsistency:
"model": { ... - "value": [] + "value": ""src/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.json (1)
1580-1588: Blocking: Prompt references CONTEXT but the field isn’t defined or wired.The template text uses {CONTEXT}/{{CONTEXT}}, yet "CONTEXT" is missing from Prompt.custom_fields.template and from Prompt.template fields, so the variable won’t resolve at runtime. Add the field and wire Chat Input → Prompt.CONTEXT.
Apply this patch to define the field and create the edge:
--- a/src/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.json +++ b/src/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.json @@ - "custom_fields": { - "template": [ + "custom_fields": { + "template": [ + "CONTEXT", "PROFILE_TYPE", "PROFILE_DETAILS", "CONTENT_GUIDELINES", "TONE_AND_STYLE", "OUTPUT_FORMAT", "OUTPUT_LANGUAGE" ] }, @@ "template": { + "CONTEXT": { + "advanced": false, + "display_name": "CONTEXT", + "dynamic": false, + "field_type": "str", + "input_types": ["Message"], + "list": false, + "load_from_db": false, + "multiline": true, + "name": "CONTEXT", + "placeholder": "", + "required": false, + "show": true, + "title_case": false, + "type": "str", + "value": "" + },And add an edge to feed the context from Chat Input:
@@ "edges": [ + { + "animated": false, + "className": "", + "data": { + "sourceHandle": { "dataType": "ChatInput", "id": "ChatInput-JpNZb", "name": "message", "output_types": ["Message"] }, + "targetHandle": { "fieldName": "CONTEXT", "id": "Prompt-JXzxV", "inputTypes": ["Message"], "type": "str" } + }, + "id": "xy-edge__ChatInput-JpNZb-message__to__Prompt-JXzxV-CONTEXT", + "selected": false, + "source": "ChatInput-JpNZb", + "sourceHandle": "{\"dataType\":\"ChatInput\",\"id\":\"ChatInput-JpNZb\",\"name\":\"message\",\"output_types\":[\"Message\"]}", + "target": "Prompt-JXzxV", + "targetHandle": "{\"fieldName\":\"CONTEXT\",\"id\":\"Prompt-JXzxV\",\"inputTypes\":[\"Message\"],\"type\":\"str\"}" + },Also applies to: 1776-1817
src/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.json (1)
2431-2461: Guard against None from Docling subprocess before rollupIf _process_docling_in_subprocess returns None, rollup_data([None]) may raise or emit invalid rows. Add a safe fallback.
- else: - # If not structured, keep as-is (e.g., markdown export or error dict) - final_return.extend(self.rollup_data(file_list, [advanced_data])) + else: + # If not structured, keep as-is (e.g., markdown export or error dict) + if advanced_data is None: + from lfx.schema.data import Data + advanced_data = Data(data={"error": "Docling returned no result", "file_path": file_path}) + final_return.extend(self.rollup_data(file_list, [advanced_data]))src/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.json (1)
1104-1105: Fix default Parser template variableDefault uses {dt}, which won’t exist; {text} is used elsewhere and in examples.
- "value": "Text: {dt}" + "value": "Text: {text}"src/backend/base/langflow/initial_setup/starter_projects/Youtube Analysis.json (1)
25-25: Re-serialize edge handle strings with proper JSON Unicode escaping.The edge ID strings contain literal
œ(U+0153) characters as intentional delimiters for handle metadata (thescape_json_parsefunction in setup.py explicitly replaces these with"for JSON parsing). However, these characters should be stored as JSON Unicode escape sequences (\u0153), not as literal UTF-8 characters in the JSON file.Other starter projects (Blog Writer.json, Custom Component Generator.json) correctly use
\u0153escaping, but this file contains literalœcharacters at lines 25, 53, 83, 111, 140, 168, 196, 224, and 252. This inconsistency suggests the file was not properly serialized through theescape_json_dumputility.Regenerate or re-serialize this file to ensure all edge handle strings use consistent JSON Unicode escaping (
\u0153), not literal characters.src/backend/base/langflow/initial_setup/starter_projects/Research Agent.json (1)
900-906: Minor: README typos and provider‑agnostic wording.
- Fix “coimponent” typo.
- Replace “OpenAI API Key” with provider‑agnostic “API Key” to match new ModelInput flow.
- Welcome to the Research Agent! ... - - Add your **OpenAI API Key** to the **Language Model**s and **Agent** Components or change the provider and add your credentials. - - Add your **Tavily API Key** to the Tavily AI Search coimponent. + Welcome to the Research Agent! ... + - Add your **API Key** in the **Language Model** and **Agent** components (choose provider in “Language Model”). + - Add your **Tavily API Key** to the Tavily AI Search component.src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json (1)
720-727: Update README note to provider‑agnostic wording.Align instructions with ModelInput flow; remove OpenAI‑specific phrasing.
-* An [OpenAI API key](https://platform.openai.com/) +* An API key for your chosen provider (set it in the Language Model component) ... -1. Paste your OpenAI API key in the **Language Model** model component. +1. Choose a provider in **Language Model** and paste the corresponding **API Key**.
🧹 Nitpick comments (30)
src/backend/base/langflow/initial_setup/starter_projects/Invoice Summarizer.json (1)
1209-1236: Clarify deprecation timeline and removal plan foragent_descriptionfield.The
agent_descriptionfield is marked as "[Deprecated]" in the display name (line 1214) with a notice that "This feature is deprecated and will be removed in future versions." However:
- The field remains fully functional and included in field_order.
- No version or timeline is specified for removal.
- The deprecation notice in the info text may confuse users.
Recommend:
- Specify a target version or date for removal (e.g., "v1.9.0 or later").
- Update tooling to emit a runtime deprecation warning when this field is used.
- Provide a migration path or document what users should do instead.
src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json (7)
3372-3397: Ollama base URL default and persistence inconsistency.Code sets a DEFAULT_OLLAMA_URL and marks load_from_db=True, but the serialized template has load_from_db=false and empty value. This prevents the default from surfacing and breaks persistence across reloads.
"ollama_base_url": { - "load_from_db": false, - "value": "" + "load_from_db": true, + "value": "http://localhost:11434" }
1001-1019: Update Read Me instructions to provider‑agnostic phrasing and fix grammar.“Add your OpenAI API key to the Language Model…” is outdated; LM now uses a generic API key. Also “Only the run the Load Data flow” has a grammar error.
-1. Add your OpenAI API key to the **Language Model** component and the two **Embeddings** components. +1. Add your model provider API key to the **Language Model** component and your OpenAI API key to the two **Embeddings** components. @@ -Only the run the **Load Data** flow when you need to populate your vector database with baseline content, such as product data. +Only run the **Load Data** flow when you need to populate your vector database with baseline content, such as product data.
2444-2469: Note near Language Model still says “Add your OpenAI API key here”.This note sits next to the Language Model node; it should be provider‑agnostic.
-"description": "### 💡 Add your OpenAI API key here 👇", +"description": "### 💡 Add your model provider API key here 👇",
4205-4213: Default search method should match guidance.Descriptions recommend Hybrid Search as suggested, but default is “Vector Search”.
- "value": "Vector Search" + "value": "Hybrid Search"Apply to both AstraDB nodes.
Also applies to: 5018-5026
5154-5156: Align last_tested_version with component versions.Root still says 1.6.4 while LM is on lf_version 1.7.0. Update to reflect the version this starter targets.
-"last_tested_version": "1.6.4", +"last_tested_version": "1.7.0",
1355-1373: Minor consistency: lf_version mismatch between the two OpenAI Embeddings nodes.One is 1.2.0 and the other 1.1.1. Not harmful, but aligning helps avoid diff churn.
Set both to the same current component lf_version.
Also applies to: 1904-1921
1556-1572: Remove this reference or confirm support for legacy embedding model.The list includes text-embedding-ada-002 alongside newer text-embedding-3 models. While OpenAI still supports text-embedding-ada-002, prefer text-embedding-3-small or text-embedding-3-large for better performance and lower costs. If legacy support is required, clarify via documentation; otherwise, remove to focus users on current recommendations.
src/backend/base/langflow/initial_setup/starter_projects/Nvidia Remix.json (1)
1541-1566: Add timeout and error handling to documentation fetchNetwork call lacks a timeout and broad error handling. Add a reasonable timeout and catch httpx exceptions.
- response = httpx.get(search_index_url, follow_redirects=True) + try: + response = httpx.get( + search_index_url, + follow_redirects=True, + timeout=10.0, + headers={"User-Agent": "langflow-starter/rtx-remix"} + ) + except httpx.HTTPError as e: + raise ValueError(f"Failed to fetch search index: {e!s}") from esrc/backend/base/langflow/initial_setup/starter_projects/Portfolio Website Code Generator.json (2)
1601-1626: Align Ollama URL field with code defaults.Template sets load_from_db=false and empty value, while code provides a DEFAULT_OLLAMA_URL and often uses load_from_db=True. Recommend aligning to avoid blank endpoint on selection.
Apply:
- "load_from_db": false, + "load_from_db": true, ... - "value": "" + "value": "http://localhost:11434"Please verify this matches current lfx runtime expectations for MessageInput. If lfx overrides template defaults at runtime, keep value empty but set load_from_db=true. As per coding guidelines, ...
642-651: Make API key notes provider‑agnostic.Update note text to avoid OpenAI‑specific wording per PR goals.
- "description": "### 💡 Add your OpenAI API key here", + "description": "### 💡 Add your API key here"Also applies to: 1749-1756
src/backend/base/langflow/initial_setup/starter_projects/Basic Prompting.json (3)
523-537: Generalize API key note.Match PR intent and LM changes by removing OpenAI‑specific wording.
- "description": "### 💡 Add your OpenAI API key here 👇", + "description": "### 💡 Add your API key here 👇",
1221-1226: Generalize flow description.Make description provider‑agnostic.
- "description": "Perform basic prompting with an OpenAI model.", + "description": "Perform basic prompting with a language model.",
1006-1031: Align Ollama URL input with runtime defaults.Same concern as other template: empty value + load_from_db=false may hide DEFAULT_OLLAMA_URL.
- "load_from_db": false, + "load_from_db": true, ... - "value": "" + "value": "http://localhost:11434"If lfx sets defaults programmatically, at least flip load_from_db to true. As per coding guidelines, ...
Also applies to: 1069-1094
src/backend/base/langflow/initial_setup/starter_projects/Basic Prompt Chaining.json (2)
29-31: Update component versions to 1.7.0.Nodes still at lf_version 1.5.0; update to match current release and other starters.
Also applies to: 164-177, 434-455, 839-840
1-986: Optional: add LM nodes consistent with new model‑centric API.Adopt the same LanguageModelComponent structure used in Basic Prompting (model/api_key/IBM/Ollama fields) to keep starters consistent.
I can generate a patched JSON with model nodes and edges wired to the existing three Prompt nodes. Want me to draft it?
src/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.json (2)
1535-1541: Update note: provider‑agnostic wording.“The OpenAI model will create the thread” is outdated. Switch to provider‑neutral “Language Model” to match ModelInput.
- - The OpenAI model will create the thread based on your specifications + - The selected Language Model will create the thread based on your specifications
2228-2233: Bump last_tested_version to match v1.7.0 updates.This starter targets the new component schema; update the flow’s last_tested_version.
- "last_tested_version": "1.4.3", + "last_tested_version": "1.7.0",src/backend/base/langflow/initial_setup/starter_projects/Market Research.json (2)
701-710: Generalize Quickstart to any provider.Docs say “OpenAI API key” and “OpenAI model,” but the flow is provider‑agnostic via ModelInput in Agent/Structured Output.
-1. Add your **OpenAI API key** to the **OpenAI** model and **Agent** components. +1. Select your provider in the **Agent** and **Structured Output** components and add the corresponding **API key** where required.
1979-2014: Normalize ModelInput default value.Elsewhere ModelInput.value is an empty list ([]). Here it’s an empty string (""), which can confuse validation/UX.
- "value": "" + "value": []src/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.json (3)
2962-2962: Project version mismatch with component lf_version 1.7.0Top-level last_tested_version is still 1.4.3. Bump to 1.7.0 to reflect the updated component schema and avoid confusion in tooling/docs.
- "last_tested_version": "1.4.3", + "last_tested_version": "1.7.0",
1254-1254: Make API key notes provider‑agnosticNotes still say “OpenAI API key” while the starter now supports multiple providers. Recommend generic wording.
- "description": "### 💡 Add your OpenAI API key here 👇", + "description": "### 💡 Add your model provider API key here 👇",Also applies to: 1283-1283, 1310-1310
663-663: Update note text to match provider‑agnostic Language Model componentThe note references “OpenAI Model Component.” Replace with “Language Model component” to reflect the new generic component.
-4. The **OpenAI Model Component** processes the text and classifies the sentiment as **Positive, Neutral, or Negative**. +4. The **Language Model** component processes the text and classifies the sentiment as **Positive, Neutral, or Negative**.src/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.json (2)
939-939: Make note text provider‑agnosticReplace “OpenAI” mentions with “Language Model” to match the generic component.
- Using **Langflow’s looping mechanism**, the template iterates through multiple research papers, translates them with the **OpenAI** model component, and outputs an aggregated version of all translated papers. + Using **Langflow’s looping mechanism**, the template iterates through multiple research papers, translates them with the **Language Model** component, and outputs an aggregated version of all translated papers. @@ - 1. Add your OpenAI API key to the **Language Model** component. + 1. Add your model provider API key to the **Language Model** component.
1831-1831: Project version mismatch with updated component schemaUpdate last_tested_version to 1.7.0 to reflect the migrated LanguageModelComponent.
- "last_tested_version": "1.4.3", + "last_tested_version": "1.7.0",src/backend/base/langflow/initial_setup/starter_projects/Research Agent.json (2)
3157-3158: Update flow’s last_tested_version to 1.7.0.The starter now targets v1.7.0; the root still says 1.4.3.
- "last_tested_version": "1.4.3", + "last_tested_version": "1.7.0",
1249-1266: Optional: Expose Tavily “DataFrame” output in node outputs for flexibility.Code defines Output(display_name="DataFrame", name="dataframe", method="fetch_content_dataframe") but node outputs only expose component_as_tool. Add a second output to allow direct wiring of search results.
"outputs": [ { "allows_loop": false, "cache": true, "display_name": "Toolset", "group_outputs": false, "hidden": null, "method": "to_toolkit", "name": "component_as_tool", "options": null, "required_inputs": null, "selected": "Tool", "tool_mode": true, "types": [ "Tool" ], "value": "__UNDEFINED__" } + , + { + "allows_loop": false, + "cache": true, + "display_name": "DataFrame", + "group_outputs": false, + "method": "fetch_content_dataframe", + "name": "dataframe", + "selected": "DataFrame", + "tool_mode": false, + "types": [ "DataFrame" ], + "value": "__UNDEFINED__" + } ],Also applies to: 1319-1323
src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json (3)
467-474: Field order uses stale key “store_message”.The input is named should_store_message in the template. Update field_order so the toggle appears in the intended position.
- "input_value", - "store_message", + "input_value", + "should_store_message",
599-620: Type should be “other” to reflect multiple accepted input_types.ChatOutput.input_value accepts Data/DataFrame/Message; type "str" is misleading.
- "type": "str", + "type": "other",
1721-1722: Update flow’s last_tested_version to 1.7.0.The flow targets the new LanguageModelComponent surface.
- "last_tested_version": "1.4.2", + "last_tested_version": "1.7.0",
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
src/frontend/package-lock.jsonis excluded by!**/package-lock.json
📒 Files selected for processing (31)
src/backend/base/langflow/initial_setup/starter_projects/Basic Prompt Chaining.json(1 hunks)src/backend/base/langflow/initial_setup/starter_projects/Basic Prompting.json(24 hunks)src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json(15 hunks)src/backend/base/langflow/initial_setup/starter_projects/Custom Component Generator.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Document Q&A.json(13 hunks)src/backend/base/langflow/initial_setup/starter_projects/Financial Report Parser.json(6 hunks)src/backend/base/langflow/initial_setup/starter_projects/Hybrid Search RAG.json(7 hunks)src/backend/base/langflow/initial_setup/starter_projects/Image Sentiment Analysis.json(3 hunks)src/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.json(35 hunks)src/backend/base/langflow/initial_setup/starter_projects/Invoice Summarizer.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Market Research.json(23 hunks)src/backend/base/langflow/initial_setup/starter_projects/Meeting Summary.json(33 hunks)src/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.json(13 hunks)src/backend/base/langflow/initial_setup/starter_projects/News Aggregator.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Nvidia Remix.json(16 hunks)src/backend/base/langflow/initial_setup/starter_projects/Pokédex Agent.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Portfolio Website Code Generator.json(23 hunks)src/backend/base/langflow/initial_setup/starter_projects/Price Deal Finder.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Research Agent.json(35 hunks)src/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.json(19 hunks)src/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.json(14 hunks)src/backend/base/langflow/initial_setup/starter_projects/SaaS Pricing.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Search agent.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Sequential Tasks Agents.json(50 hunks)src/backend/base/langflow/initial_setup/starter_projects/Simple Agent.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Social Media Agent.json(17 hunks)src/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.json(38 hunks)src/backend/base/langflow/initial_setup/starter_projects/Travel Planning Agents.json(51 hunks)src/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.json(19 hunks)src/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json(25 hunks)src/backend/base/langflow/initial_setup/starter_projects/Youtube Analysis.json(26 hunks)
🧰 Additional context used
🧠 Learnings (9)
📚 Learning: 2025-06-23T12:46:42.048Z
Learnt from: CR
Repo: langflow-ai/langflow PR: 0
File: .cursor/rules/frontend_development.mdc:0-0
Timestamp: 2025-06-23T12:46:42.048Z
Learning: React Flow should be used for flow graph visualization, with nodes and edges passed as props, and changes handled via onNodesChange and onEdgesChange callbacks.
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/Basic Prompt Chaining.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Hybrid Search RAG.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Market Research.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Document Q&A.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Custom Component Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json
📚 Learning: 2025-11-24T19:46:45.790Z
Learnt from: CR
Repo: langflow-ai/langflow PR: 0
File: .cursor/rules/frontend_development.mdc:0-0
Timestamp: 2025-11-24T19:46:45.790Z
Learning: Applies to src/frontend/src/components/**/*.{tsx,jsx} : Use React Flow for flow graph visualization with Node, Edge, Controls, and Background components
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/Basic Prompt Chaining.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Image Sentiment Analysis.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Hybrid Search RAG.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Market Research.jsonsrc/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Document Q&A.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Custom Component Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Portfolio Website Code Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Meeting Summary.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json
📚 Learning: 2025-06-23T12:46:42.048Z
Learnt from: CR
Repo: langflow-ai/langflow PR: 0
File: .cursor/rules/frontend_development.mdc:0-0
Timestamp: 2025-06-23T12:46:42.048Z
Learning: Custom React Flow node types should be implemented as memoized components, using Handle components for connection points and supporting optional icons and labels.
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/Basic Prompt Chaining.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Memory Chatbot.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Hybrid Search RAG.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Market Research.jsonsrc/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Document Q&A.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Basic Prompting.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Custom Component Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Portfolio Website Code Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Meeting Summary.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json
📚 Learning: 2025-11-24T19:46:09.104Z
Learnt from: CR
Repo: langflow-ai/langflow PR: 0
File: .cursor/rules/backend_development.mdc:0-0
Timestamp: 2025-11-24T19:46:09.104Z
Learning: Backend components should be structured with clear separation of concerns: agents, data processing, embeddings, input/output, models, text processing, prompts, tools, and vector stores
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/Sequential Tasks Agents.jsonsrc/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Search agent.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Custom Component Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Research Agent.json
📚 Learning: 2025-06-26T19:43:18.260Z
Learnt from: ogabrielluiz
Repo: langflow-ai/langflow PR: 0
File: :0-0
Timestamp: 2025-06-26T19:43:18.260Z
Learning: In langflow custom components, the `module_name` parameter is now propagated through template building functions to add module metadata and code hashes to frontend nodes for better component tracking and debugging.
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Document Q&A.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Basic Prompting.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Custom Component Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Portfolio Website Code Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Meeting Summary.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json
📚 Learning: 2025-06-23T12:46:29.953Z
Learnt from: CR
Repo: langflow-ai/langflow PR: 0
File: .cursor/rules/docs_development.mdc:0-0
Timestamp: 2025-06-23T12:46:29.953Z
Learning: All terminology such as 'Langflow', 'Component', 'Flow', 'API', and 'JSON' must be capitalized or uppercased as specified in the terminology section.
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Document Q&A.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Basic Prompting.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Meeting Summary.json
📚 Learning: 2025-11-24T19:46:09.104Z
Learnt from: CR
Repo: langflow-ai/langflow PR: 0
File: .cursor/rules/backend_development.mdc:0-0
Timestamp: 2025-11-24T19:46:09.104Z
Learning: Applies to src/backend/base/langflow/components/**/*.py : Add new components to the appropriate subdirectory under `src/backend/base/langflow/components/` (agents/, data/, embeddings/, input_output/, models/, processing/, prompts/, tools/, or vectorstores/)
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Search agent.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Instagram Copywriter.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Vector Store RAG.json
📚 Learning: 2025-11-24T19:46:26.770Z
Learnt from: CR
Repo: langflow-ai/langflow PR: 0
File: .cursor/rules/docs_development.mdc:0-0
Timestamp: 2025-11-24T19:46:26.770Z
Learning: Applies to docs/docs/**/*.{md,mdx} : Use sentence case for headers and proper capitalization for terminology: Langflow, Component, Flow, API, JSON
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/Document Q&A.json
📚 Learning: 2025-06-23T12:46:52.420Z
Learnt from: CR
Repo: langflow-ai/langflow PR: 0
File: .cursor/rules/icons.mdc:0-0
Timestamp: 2025-06-23T12:46:52.420Z
Learning: When implementing a new component icon in Langflow, ensure the icon name is clear, recognizable, and used consistently across both backend (Python 'icon' attribute) and frontend (React/TypeScript mapping).
Applied to files:
src/backend/base/langflow/initial_setup/starter_projects/Document Q&A.jsonsrc/backend/base/langflow/initial_setup/starter_projects/Basic Prompting.json
⏰ 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). (16)
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 1
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 3
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 5
- GitHub Check: Lint Backend / Run Mypy (3.12)
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 2
- GitHub Check: Run Backend Tests / Unit Tests - Python 3.10 - Group 4
- GitHub Check: Lint Backend / Run Mypy (3.13)
- GitHub Check: Lint Backend / Run Mypy (3.10)
- GitHub Check: Run Backend Tests / Integration Tests - Python 3.10
- GitHub Check: Lint Backend / Run Mypy (3.11)
- GitHub Check: Run Frontend Unit Tests / Frontend Jest Unit Tests
- GitHub Check: Run Backend Tests / LFX Tests - Python 3.10
- GitHub Check: Test Docker Images / Test docker images
- GitHub Check: Test Starter Templates
- GitHub Check: Optimize new Python code in this PR
- GitHub Check: test-starter-projects
src/backend/base/langflow/initial_setup/starter_projects/Basic Prompt Chaining.json
Outdated
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/Blog Writer.json
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/News Aggregator.json
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/Pokédex Agent.json
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/Research Agent.json
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.json
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/Research Translation Loop.json
Outdated
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/SEO Keyword Generator.json
Outdated
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/Text Sentiment Analysis.json
Show resolved
Hide resolved
src/backend/base/langflow/initial_setup/starter_projects/Twitter Thread Generator.json
Show resolved
Hide resolved
Co-Authored-By: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
github-actions
bot
added
bug
Co-Authored-By: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
github-actions
bot
added
bug
Co-Authored-By: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
github-actions
bot
added
bug
Co-Authored-By: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
github-actions
bot
added
bug
Co-Authored-By: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
github-actions
bot
added
bug
github-actions
bot
added
bug
github-actions
bot
added
bug
github-actions
bot
added
bug
github-actions
bot
added
bug
Co-Authored-By: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
github-actions
bot
added
bug
2 participants
This pull request updates the
Basic Prompting.jsonstarter project for Langflow to align with version 1.7.0 and improve component configuration, documentation, and flow structure. The changes modernize the flow, update component versions, enhance clarity for users, and add new options for language model configuration.Key changes include:
Flow and Node Structure Updates:
ChatInput,Prompt,ChatOutput, andLanguageModelComponentnodes and their connections. [1] [2] [3] [4] [5] [6] [7] [8] [9] [10]Component Version and Metadata Updates:
lf_versionto1.7.0for all relevant components, ensuring compatibility with the latest Langflow features. [1] [2] [3] [4]LanguageModelComponentto use the new module path, reduced dependencies, and added new metadata fields such aslast_updated.Language Model Component Enhancements:
LanguageModelComponent, includingbase_url_ibm_watsonx,project_id, andollama_base_url, and updated the input field order. The API key field is now more generic and not loaded from the database by default. [1] [2]_frontend_node_flow_idand_frontend_node_folder_idto support frontend integration.Documentation and Usability Improvements:
selectedproperty on the output node totruefor better default UX.Output and Method Metadata:
loop_types,options, andrequired_inputsto output and method definitions, preparing for future extensibility. [1] [2]These updates collectively modernize the starter project, making it more extensible, user-friendly, and compatible with the latest Langflow features.
Summary by CodeRabbit
Release Notes
New Features
Improvements
✏️ Tip: You can customize this high-level summary in your review settings.