Merge branch 'main' into feat/support-tongyi

.github/workflows/python_test.yml

@@ -145,13 +145,16 @@ jobs:
         if: steps.check-version.outputs.skipped == 'false'
         run: |
           make build main=true
-      - name: Install wheel
+      - name: Install wheel and Test CLI
         if: steps.check-version.outputs.skipped == 'false'
         run: |
-          python -m pip install dist/*.whl
+          uv venv new-venv
+          source new-venv/bin/activate
+          uv pip install dist/*.whl
       - name: Test CLI
         if: steps.check-version.outputs.skipped == 'false'
         run: |
+          source new-venv/bin/activate
           python -m langflow run --host 127.0.0.1 --port 7860 --backend-only &
           SERVER_PID=$!
           # Wait for the server to start

.gitignore

@@ -276,4 +276,4 @@ src/frontend/temp
 .history
 
 .dspy_cache/
-cache.db
+*.db

docs/docs/Configuration/configuration-custom-database.md

@@ -0,0 +1,76 @@
+---
+title: Configure an external PostgreSQL database
+sidebar_position: 8
+---
+Langflow's default database is [SQLite](https://www.sqlite.org/docs.html), but you can configure Langflow to use PostgreSQL instead.
+
+This guide will walk you through the process of setting up an external database for Langflow by replacing the default SQLite connection string `sqlite:///./langflow.db` with PostgreSQL.
+
+## Prerequisite
+
+* A [PostgreSQL](https://www.pgadmin.org/download/) database
+
+## Connect Langflow to PostgreSQL
+
+To connect Langflow to PostgreSQL, follow these steps.
+
+1. Find your PostgreSQL database's connection string.
+It looks like `postgresql://user:password@host:port/dbname`.
+For example, if you started PostgreSQL with this Docker command:
+
+```
+docker run --name some-postgres -e POSTGRES_PASSWORD=mysecretpassword -d -p 5432:5432 postgres
+```
+
+Your connection string would be `postgresql://some-postgres:mysecretpassword@localhost:5432/postgres`.
+
+2. Create a `.env` file for configuring Langflow.
+```
+touch .env
+```
+
+3. To set the database URL environment variable, add it to your `.env` file:
+```plaintext
+LANGFLOW_DATABASE_URL="postgresql://user:password@localhost:5432/dbname"
+```
+
+:::tip
+The Langflow project includes a [`.env.example`](https://github.com/langflow-ai/langflow/blob/main/.env.example) file to help you get started.
+You can copy the contents of this file into your own `.env` file and replace the example values with your own preferred settings.
+Replace the value for `LANGFLOW_DATABASE_URL` with your PostgreSQL connection string.
+:::
+
+4. Run Langflow with the `.env` file:
+```bash
+langflow run --env-file .env
+```
+
+5. In Langflow, create traffic by running a flow.
+6. Inspect your PostgreSQL deployment's tables and activity.
+You will see new tables and traffic created.
+
+## Example Langflow and PostgreSQL docker-compose.yml
+
+The Langflow project includes a [`docker-compose.yml`](https://github.com/langflow-ai/langflow/blob/main/docker_example/docker-compose.yml) file  for quick deployment with PostgreSQL.
+
+This configuration launches Langflow and PostgreSQL containers, with Langflow pre-configured to use the PostgreSQL database. Customize the database credentials as needed.
+
+To start the services, navigate to the `/docker_example` directory, and then run `docker-compose up`.
+
+```yaml
+services:
+  langflow:
+    image: langflow-ai/langflow:latest
+    environment:
+      - LANGFLOW_DATABASE_URL=postgresql://user:password@postgres:5432/langflow
+    depends_on:
+      - postgres
+
+  postgres:
+    image: postgres:15
+    environment:
+      - POSTGRES_USER=user
+      - POSTGRES_PASSWORD=password
+      - POSTGRES_DB=langflow
+```
+

docs/docs/Guides/guides-chat-memory.md

@@ -6,7 +6,7 @@ slug: /guides-chat-memory
 
 
 
-Langflow allows every chat message to be stored, and a single flow can have multiple memory sessions. This enables you to create separate _memories_ for agents to store and recall information as needed. 
+Langflow allows every chat message to be stored, and a single flow can have multiple memory sessions. This enables you to create separate _memories_ for agents to store and recall information as needed.
 
 
 In any project, as long as there are [**Chat**](/components-io) being used, memories are always being stored by default. These are messages from a user to the AI or vice-versa.
@@ -26,7 +26,7 @@ Memories can be visualized and managed directly from the **Playground**. You can
 
 Modifying these memories will influence the behavior of the chatbot responses, as long as an agent uses them. Here you have the ability to remove or edit previous messages, allowing them to manipulate and explore how these changes affect model responses.
 
-To modify chat memories, click your **Flow Name**, and then click **Logs**.
+To modify chat memories, from the playground, click the **Options** menu of any session, and then select **Message Logs**.
 
 
 ![](/img/logs.png)
@@ -45,7 +45,7 @@ The **Chat Memory** component also retrieves message histories by `Session ID`,
 
 ![](/img/chat-input-controls-pane.png)
 
-By default, if the `Session ID`  value is empty, it is set to match the the same value as the `Flow ID`. 
+By default, if the `Session ID` value is empty, it is set to the same value as `Flow ID`.
 
 You can also display all messages stored across every flow and session by going to **Settings** > **Messages**.
 

docs/docs/Guides/guides-data-message.md

@@ -60,28 +60,38 @@ print(data.title)  # Outputs: "Hello, World!" because "title" key is in the data
 The `Data` object is also convenient for visualization of outputs, since the output preview has visual elements to inspect data as a table and its cells as pop ups for basic types. The idea is to create a unified way to work and visualize complex information in Langflow.
 
 
-To receive `Data` objects in a component input, you can use the `DataInput` input type. 
+To receive `Data` objects in a component input, you can use the `DataInput` input type.
 
 
-## The Message Object {#f4f17cad02a545068f407d515cbc2902}
+## Message object attributes {#f4f17cad02a545068f407d515cbc2902}
 
 
 ---
 
 
 The `Message` object extends the functionality of `Data` and includes additional attributes and methods for chat interactions.
 
-- **Main Attributes:**
-	- `text_key`: Key to retrieve the primary text data.
-	- `text`: The main text content of the message.
-	- `sender`: Identifier for the sender (e.g., "User" or "AI").
-	- `sender_name`: Name of the sender.
-	- `files`: List of files associated with the message.
-	- `session_id`: Identifier for the chat session.
-	- `timestamp`: Timestamp when the message was created.
-	- `flow_id`: Identifier for the flow.
-
-The `Message` object can be used to send, store and manipulate chat messages within Langflow. You can create a `Message` object by directly assigning key-value pairs to it. For example:
+
+- **Core message data:**
+  - `text`: The main text content of the message
+  - `sender`: Identifier for the sender (e.g., "User" or "AI")
+  - `sender_name`: Name of the sender
+  - `session_id`: Identifier for the chat session
+  - `timestamp`: Timestamp when the message was created (UTC)
+  - `flow_id`: Identifier for the flow
+  - `id`: Unique identifier for the message
+
+- **Content and files:**
+  - `files`: List of files or images associated with the message
+  - `content_blocks`: List of structured content blocks
+  - `properties`: Additional properties including visual styling and source information
+
+- **Message state:**
+  - `error`: Boolean indicating if there was an error
+  - `edit`: Boolean indicating if the message was edited
+  - `category`: Message category ("message", "error", "warning", "info")
+
+The `Message` object can be used to send, store, and manipulate chat messages within Langflow. You can create a `Message` object by directly assigning key-value pairs to it. For example:
 
 
 ```python

docs/docs/Workspace/workspace-overview.md

@@ -26,7 +26,7 @@ The **Playground** executes the current flow in the workspace.
 
 Chat with your flow, view inputs and outputs, and modify your AI's memories to tune your responses in real time.
 
-Any input or output component can be opened in the **Playground** and tested in real time.
+Either the **Chat Input** or **Chat Output** component can be opened in the **Playground** and tested in real time.
 
 For more information, see the [Playground documentation](/workspace-playground).
 

docs/docs/Workspace/workspace-playground.md

@@ -22,22 +22,19 @@ Notice how the **Playground's** window arrangement changes depending on what com
 :::
 
 
-You can also open a flow's **Playground** without entering its workspace. From **My Collections** or **Langflow Store**, click the **Playground** in one of the projects card.
-
-
 ## Memory Management {#821a5ee2a8a44d35b49943cba630511c}
 
 
 ---
 
-Click the Memories tab to open a table of previous interactions for a specific flow.
+When you send a message from the **Playground** interface, the interactions for that session are stored in the **Message Logs**.
 
-Whenever you send a message from the **Playground** interface, under the **Memories** tab you'll see a table of previous interactions for that session.
-
-Langflow allows every chat message to be stored, and a single flow can have multiple memory sessions.
+Langflow allows every chat message to be stored, and a single flow can have multiple chat sessions.
 
 Chat conversations store messages categorized by a Session ID. A single flow can host multiple Session IDs, and different flows can share the same Session ID.
 
+To view messages by session ID, from the Playground, click the Options menu of any session, and then select Message Logs.
+
 Individual messages in chat memory can be edited or deleted. Modifying these memories will influence the behavior of the chatbot responses.
 
 To learn more about memories in Langflow, see [Chat Memory](/guides-chat-memory).
@@ -63,7 +60,7 @@ curl -X POST \
 }'
 ```
 
-Check your flow’s Memories tab. In addition to the messages stored for the Default Session, a new chat session is started with your new Session ID.
+Check your flow's **Playground**. In addition to the messages stored for the Default Session, a new session is started with your new Session ID.
 
 **Chat Input** and **Chat Output** components can also store a `session_id` parameter as a **Tweak** for specific sessions. The Playground will still display all available sessions, but the flow will use the value stored in the `session_id` tweak.
 

pyproject.toml

@@ -32,90 +32,86 @@ maintainers = [
 # Define your main dependencies here
 dependencies = [
     "langflow-base==0.1.0",
-    "beautifulsoup4>=4.12.2",
-    "google-search-results>=2.4.1",
-    "google-api-python-client>=2.130.0",
-    "huggingface-hub[inference]>=0.23.2",
-    "networkx>=3.1",
-    "fake-useragent>=1.5.0",
-    "pyarrow>=14.0.0",
-    "wikipedia>=1.4.0",
+    "beautifulsoup4>=4.12.2,<5.0.0",
+    "google-search-results>=2.4.1,<3.0.0",
+    "google-api-python-client>=2.130.0,<3.0.0",
+    "huggingface-hub[inference]>=0.23.2,<1.0.0",
+    "networkx>=3.1,<4.0.0",
+    "fake-useragent>=1.5.0,<2.0.0",
+    "pyarrow>=14.0.0,<18.0.0",
+    "wikipedia>=1.4.0,<2.0.0",
     "qdrant-client~=1.9.2",
-    "weaviate-client>=4.8",
-    "cohere>=5.5.3",
-    "faiss-cpu>=1.8.0",
-    "types-cachetools>=5.3.0.5",
-    "pymongo>=4.6.0",
+    "weaviate-client>=4.8,<5.0.0",
+    "cohere>=5.5.3,<6.0.0",
+    "faiss-cpu>=1.8.0,<2.0.0",
+    "types-cachetools>=5.3.0.5,<6.0.0",
+    "pymongo>=4.6.0,<5.0.0",
     "supabase~=2.6.0",
     "certifi>=2023.11.17,<2025.0.0",
-    "fastavro>=1.8.0",
-    "redis>=5.0.1",
-    "metaphor-python>=0.1.11",
-    'pywin32>=306; sys_platform == "win32"',
+    "fastavro>=1.8.0,<2.0.0",
+    "redis>=5.0.1,<6.0.0",
+    "metaphor-python>=0.1.11,<1.0.0",
+    'pywin32>=306,<307; sys_platform == "win32"',
     "langfuse~=2.53.1",
-    "metal-sdk>=2.5.0",
-    "markupsafe>=2.1.3",
+    "metal-sdk>=2.5.0,<3.0.0",
+    "markupsafe>=2.1.3,<4.0.0",
     "boto3~=1.34.162",
-    "numexpr>=2.8.6",
+    "numexpr>=2.8.6,<3.0.0",
     "qianfan==0.3.5",
-    "pgvector>=0.2.3",
-    "pyautogen>=0.2.0",
+    "pgvector>=0.2.3,<1.0.0",
+    "pyautogen>=0.2.0,<1.0.0",
     "langchain~=0.3.3",
-    "elasticsearch>=8.12.0",
-    "pytube>=15.0.0",
-    "dspy-ai>=2.4.0",
-    "assemblyai>=0.33.0",
-    "litellm>=1.44.0",
-    "chromadb>=0.4",
-    "zep-python>=2.0.0",
-    "langchain-groq>=0.1.9",
-    "langchain-pinecone>=0.1.3",
-    "youtube-transcript-api>=0.6.2",
-    "markdown>=3.7",
-    "upstash-vector>=0.5.0",
-    "gitpython>=3.1.43",
-    "kubernetes>=30.1.0",
-    "firecrawl-py==1.5.0",
-    "json-repair>=0.25.2",
-    "langchain-google-calendar-tools>=0.0.1",
-    "langchain-milvus>=0.1.1",
+    "elasticsearch>=8.12.0,<9.0.0",
+    "pytube>=15.0.0,<16.0.0",
+    "dspy-ai>=2.4.0,<3.0.0",
+    "assemblyai>=0.33.0,<1.0.0",
+    "litellm>=1.44.0,<2.0.0",
+    "chromadb>=0.4,<1.0.0",
+    "zep-python>=2.0.0,<3.0.0",
+    "langchain-groq>=0.1.9,<1.0.0",
+    "langchain-pinecone>=0.1.3,<1.0.0",
+    "youtube-transcript-api>=0.6.2,<1.0.0",
+    "markdown>=3.7,<4.0.0",
+    "upstash-vector>=0.5.0,<1.0.0",
+    "gitpython>=3.1.43,<4.0.0",
+    "kubernetes>=30.1.0,<32.0.0",
+    "json-repair>=0.25.2,<1.0.0",
+    "langchain-google-calendar-tools>=0.0.1,<1.0.0",
+    "langchain-milvus>=0.1.1,<1.0.0",
     "langwatch==0.1.16",
     "langsmith~=0.1.136",
-    "yfinance>=0.2.40",
-    "wolframalpha>=5.1.3",
+    "yfinance>=0.2.40,<1.0.0",
+    "wolframalpha>=5.1.3,<6.0.0",
     "astra-assistants[tools]~=2.2.6",
-    "composio-langchain==0.5.9",
-    "spider-client>=0.0.27",
-    "nltk>=3.9.1",
-    "lark>=1.2.2",
-    "jq>=1.8.0",
+    "composio-langchain==0.5.42",
+    "spider-client>=0.0.27,<1.0.0",
+    "nltk>=3.9.1,<4.0.0",
+    "lark>=1.2.2,<2.0.0",
+    "jq>=1.8.0,<2.0.0",
     "pydantic-settings==2.4.0",
-    "ragstack-ai-knowledge-store>=0.2.1",
-    "duckduckgo-search>=6.3.4",
-    "opensearch-py>=2.7.1",
-    "langchain-google-genai>=1.0.8",
-    "langchain-cohere>=0.1.5",
-    "langchain-anthropic>=0.1.23",
+    "ragstack-ai-knowledge-store>=0.2.1,<1.0.0",
+    "duckduckgo-search>=6.3.4,<7.0.0",
+    "opensearch-py>=2.7.1,<3.0.0",
+    "langchain-google-genai>=2.0.1,<3.0.0",
+    "langchain-cohere>=0.1.5,<1.0.0",
+    "langchain-anthropic>=0.1.23,<1.0.0",
     "langchain-astradb~=0.5.2",
     "langchain-openai~=0.2.2",
     "langchain-google-vertexai~=2.0.5",
-    "langchain-groq>=0.1.9",
+    "langchain-groq>=0.1.9,<1.0.0",
     "langchain-pinecone~=0.2.0",
     "langchain-mistralai~=0.2.0",
-    "langchain-chroma>=0.1.1",
-    "langchain-aws>=0.1.16",
+    "langchain-chroma>=0.1.1,<1.0.0",
+    "langchain-aws>=0.1.16,<1.0.0",
     "langchain-unstructured~=0.1.5",
-    "langchain-mongodb>=0.1.6",
+    "langchain-mongodb>=0.1.6,<1.0.0",
     "langchain-nvidia-ai-endpoints~=0.3.0",
-    "langchain-google-calendar-tools>=0.0.1",
-    "langchain-milvus>=0.1.1",
     "langchain-google-community~=2.0.1",
-    "langchain-elasticsearch>=0.2.0",
-    "opensearch-py>=2.7.1",
-    "langchain-ollama>=0.2.0",
-    "sqlalchemy[aiosqlite,postgresql_psycopg2binary,postgresql_psycopgbinary]>=2.0.36",
-    "atlassian-python-api>=3.41.16",
-    "mem0ai>=0.1.26",
+    "langchain-elasticsearch>=0.2.0,<1.0.0",
+    "langchain-ollama>=0.2.0,<1.0.0",
+    "sqlalchemy[aiosqlite,postgresql_psycopg2binary,postgresql_psycopgbinary]>=2.0.36,<3.0.0",
+    "atlassian-python-api>=3.41.16,<4.0.0",
+    "mem0ai>=0.1.26,<1.0.0",
 ]
 
 [project.urls]
@@ -180,7 +176,7 @@ dev-dependencies = [
     "asgi-lifespan>=2.1.0",
     "pytest-github-actions-annotate-failures>=0.2.0",
     "pytest-codspeed>=3.0.0",
-    "forbiddenfruit>=0.1.4",
+    "blockbuster>=1.1.1,<1.2",
 ]