docs: remove Guides, add pages on other categories, add Types (#4881)
* Adds Chat Memory on Components * Removes Guides * Adds Types * Fix links that referenced Guides * combine-files * redirects * content * fix(docs): update sidebar position and redirect path in configuration files * feat(docs): update memory components documentation and sidebar links * feat(docs): enhance configuration documentation with ContentBlock and DataFrame examples * add-link-for-pydantic-baseclass * update-links --------- Co-authored-by: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
This commit is contained in:
Lucas Oliveira
GitHub
parent
d790761ff0
commit
a6bebd5fcb
15 changed files with 246 additions and 254 deletions
|
|
@ -11,7 +11,7 @@ Helper components provide utility functions to help manage data, tasks, and othe
|
|||
|
||||
Chat memory in Langflow is stored either in local Langflow tables with `LCBufferMemory`, or connected to an external database.
|
||||
|
||||
The **Store Message** helper component stores chat memories as [Data](/guides-data-message) objects, and the **Message History** helper component retrieves chat messages as data objects or strings.
|
||||
The **Store Message** helper component stores chat memories as [Data](/configuration-objects) objects, and the **Message History** helper component retrieves chat messages as data objects or strings.
|
||||
|
||||
This example flow stores and retrieves chat history from an [AstraDBChatMemory](/components-memories#astradbchatmemory-component) component with **Store Message** and **Chat Memory** components.
|
||||
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ The difference between Chat Input and Text Input components is the output format
|
|||
|
||||
This component collects user input from the chat.
|
||||
|
||||
The Chat Input component creates a [Message](/guides-data-message) object that includes the input text, sender information, session ID, file attachments, and styling properties. It can optionally store the message in a chat history and supports customization of the message appearance.
|
||||
The Chat Input component creates a [Message](/configuration-objects) object that includes the input text, sender information, session ID, file attachments, and styling properties. It can optionally store the message in a chat history and supports customization of the message appearance.
|
||||
|
||||
### Inputs
|
||||
|
||||
|
|
@ -56,7 +56,7 @@ The Text Input component offers one input field for text, while the Chat Input h
|
|||
|
||||
## Chat Output
|
||||
|
||||
The Chat Output component creates a [Message](/guides-data-message) object that includes the input text, sender information, session ID, and styling properties. It can optionally store the message in a chat history and supports customization of the message appearance, including background color, icon, and text color.
|
||||
The Chat Output component creates a [Message](/configuration-objects) object that includes the input text, sender information, session ID, and styling properties. It can optionally store the message in a chat history and supports customization of the message appearance, including background color, icon, and text color.
|
||||
|
||||
### Inputs
|
||||
|
||||
|
|
@ -81,7 +81,7 @@ The Chat Output component creates a [Message](/guides-data-message) object that
|
|||
|
||||
## Text Output
|
||||
|
||||
The TextOutputComponent displays text output in the **Playground**. It takes a single input of text and returns a [Message](/guides-data-message) object containing that text. The component is simpler compared to the Chat Output, but focuses solely on displaying text without additional chat-specific features or customizations.
|
||||
The TextOutputComponent displays text output in the **Playground**. It takes a single input of text and returns a [Message](/configuration-objects) object containing that text. The component is simpler compared to the Chat Output, but focuses solely on displaying text without additional chat-specific features or customizations.
|
||||
|
||||
## Inputs
|
||||
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ Loaders fetch data into Langflow from various sources, such as databases, websit
|
|||
## Use a loader component in a flow
|
||||
|
||||
This flow creates a question-and-answer chatbot for documents that are loaded into the flow.
|
||||
The [Unstructured.io](https://unstructured.io/) loader component loads files from your local machine, and then parses them into a list of structured [Data](/guides-data-message) objects. This loaded data informs the **Open AI** component's responses to your questions.
|
||||
The [Unstructured.io](https://unstructured.io/) loader component loads files from your local machine, and then parses them into a list of structured [Data](/configuration-objects) objects. This loaded data informs the **Open AI** component's responses to your questions.
|
||||
|
||||
|
||||
|
||||
|
|
@ -62,7 +62,7 @@ The GitLoader component uses the GitLoader from LangChain to fetch and load docu
|
|||
|
||||
## Unstructured
|
||||
|
||||
This component uses the [Unstructured.io](https://unstructured.io/) Serverless API to load and parse files into a list of structured [Data](/guides-data-message) objects.
|
||||
This component uses the [Unstructured.io](https://unstructured.io/) Serverless API to load and parse files into a list of structured [Data](/configuration-objects) objects.
|
||||
|
||||
### Inputs:
|
||||
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ Memory components provide access to their respective external databases **as mem
|
|||
|
||||
This example flow stores and retrieves chat history from an **Astra DB Chat Memory** component with **Store Message** and **Chat Memory** components.
|
||||
|
||||
The **Store Message** helper component stores chat memories as [Data](/guides-data-message) objects, and the **Message History** helper component retrieves chat messages as [Data](/guides-data-message) objects or strings.
|
||||
The **Store Message** helper component stores chat memories as [Data](/configuration-objects) objects, and the **Message History** helper component retrieves chat messages as [Data](/configuration-objects) objects or strings.
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@ Refer to your specific component's documentation for more information on paramet
|
|||
|
||||
Model components receive inputs and prompts for generating text, and the generated text is sent to an output component.
|
||||
|
||||
The model output can also be sent to the **Language Model** port and on to a **Parse Data** component, where the output can be parsed into structured [Data](/guides-data-message) objects.
|
||||
The model output can also be sent to the **Language Model** port and on to a **Parse Data** component, where the output can be parsed into structured [Data](/configuration-objects) objects.
|
||||
|
||||
This example has the OpenAI model in a chatbot flow. For more information, see the [Basic prompting flow](/starter-projects-basic-prompting).
|
||||
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ Processing components process and transform data within a flow.
|
|||
|
||||
## Use a processing component in a flow
|
||||
|
||||
The **Split Text** processing component in this flow splits the incoming [data](/guides-data-message) into chunks to be embedded into the vector store component.
|
||||
The **Split Text** processing component in this flow splits the incoming [data](/configuration-objects) into chunks to be embedded into the vector store component.
|
||||
|
||||
The component offers control over chunk size, overlap, and separator, which affect context and granularity in vector store retrieval results.
|
||||
|
||||
|
|
|
|||
|
|
@ -23,7 +23,7 @@ This vector data can then be retrieved for workloads like Retrieval Augmented Ge
|
|||
|
||||
|
||||
|
||||
The user's chat input is embedded and compared to the vectors embedded during document ingestion for a similarity search. The results are output from the vector database component as a [Data](/guides-data-message) object, and parsed into text. This text fills the `{context}` variable in the **Prompt** component, which informs the **Open AI model** component's responses.
|
||||
The user's chat input is embedded and compared to the vectors embedded during document ingestion for a similarity search. The results are output from the vector database component as a [Data](/configuration-objects) object, and parsed into text. This text fills the `{context}` variable in the **Prompt** component, which informs the **Open AI model** component's responses.
|
||||
|
||||
Alternatively, connect the vector database component's **Retriever** port to a [retriever tool](components-tools#retriever-tool), and then to an [agent](/components-agents) component. This enables the agent to use your vector database as a tool and make decisions based on the available data.
|
||||
|
||||
|
|
|
|||
206
docs/docs/Configuration/configuration-objects.md
Normal file
206
docs/docs/Configuration/configuration-objects.md
Normal file
|
|
@ -0,0 +1,206 @@
|
|||
---
|
||||
title: Langflow objects
|
||||
slug: /configuration-objects
|
||||
---
|
||||
|
||||
In Langflow, the Data and Message objects are Pydantic models that serve as structured, functional representations of data.
|
||||
|
||||
## Data object
|
||||
|
||||
The `Data` object is a [Pydantic](https://docs.pydantic.dev/latest/api/base_model/) model that serves as a container for storing and manipulating data. It carries `data`—a dictionary that can be accessed as attributes—and uses `text_key` to specify which key in the dictionary should be considered the primary text content.
|
||||
|
||||
- **Main Attributes:**
|
||||
- `text_key`: Specifies the key to retrieve the primary text data.
|
||||
- `data`: A dictionary to store additional data.
|
||||
- `default_value`: default value when the `text_key` is not present in the `data` dictionary.
|
||||
|
||||
### Create a Data Object
|
||||
|
||||
Create a `Data` object by directly assigning key-value pairs to it. For example:
|
||||
|
||||
```python
|
||||
from langflow.schema import Data
|
||||
|
||||
# Creating a Data object with specified key-value pairs
|
||||
data = Data(text="my_string", bar=3, foo="another_string")
|
||||
|
||||
# Outputs:
|
||||
print(data.text) # Outputs: "my_string"
|
||||
print(data.bar) # Outputs: 3
|
||||
print(data.foo) # Outputs: "another_string"
|
||||
```
|
||||
|
||||
The `text_key` specifies which key in the `data` dictionary should be considered the primary text content. The `default_value` provides a fallback if the `text_key` is not present.
|
||||
|
||||
```python
|
||||
# Creating a Data object with a specific text_key and default_value
|
||||
data = Data(data={"title": "Hello, World!"}, text_key="content", default_value="No content available")
|
||||
|
||||
# Accessing the primary text using text_key and default_value
|
||||
print(data.get_text()) # Outputs: "No content available" because "content" key is not in the data dictionary
|
||||
|
||||
# Accessing data keys by calling the attribute directly
|
||||
print(data.title) # Outputs: "Hello, World!" because "title" key is in the data dictionary
|
||||
```
|
||||
|
||||
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, use the `DataInput` input type.
|
||||
|
||||
```python
|
||||
inputs = [
|
||||
DataInput(name="data", display_name="Data", info="Helpful info about the incoming data object.", is_list=True),
|
||||
]
|
||||
```
|
||||
|
||||
## Message object
|
||||
|
||||
The `Message` object extends the functionality of `Data` and includes additional attributes and methods for chat interactions.
|
||||
|
||||
- **Core message data:**
|
||||
|
||||
- `text`: The main text content of the message
|
||||
- `sender`: Identifier for the sender ("User" or "AI")
|
||||
- `sender_name`: Name of the sender
|
||||
- `session_id`: Identifier for the chat session (`string` or `UUID`)
|
||||
- `timestamp`: Timestamp when the message was created (UTC)
|
||||
- `flow_id`: Identifier for the flow (`string` or `UUID`)
|
||||
- `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 block objects
|
||||
- `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.
|
||||
|
||||
### Create a Message object
|
||||
|
||||
You can create a `Message` object by directly assigning key-value pairs to it. For example:
|
||||
|
||||
```python
|
||||
from langflow.schema.message import Message
|
||||
|
||||
message = Message(text="Hello, AI!", sender="User", sender_name="John Doe")
|
||||
```
|
||||
|
||||
To receive `Message` objects in a component input, you can use the `MessageInput` input type or `MessageTextInput` when the goal is to extract just the `text` field of the `Message` object.
|
||||
|
||||
## ContentBlock object
|
||||
|
||||
The `ContentBlock` object is a list of multiple `ContentTypes`. It allows you to include multiple types of content within a single `Message`, including images, videos, and text.
|
||||
|
||||
Content types are Pydantic base classes constructed from the types in [content_types.py](https://github.com/langflow-ai/langflow/blob/main/src/backend/base/langflow/schema/content_types.py).
|
||||
|
||||
Each content type has specific fields related to its data type. For example:
|
||||
|
||||
* `TextContent` has a `text` field for storing strings of text
|
||||
* `MediaContent` has a `urls` field for storing media file URLs
|
||||
* `CodeContent` has `code` and `language` fields for code snippets
|
||||
* `JSONContent` has a `data` field for storing arbitrary JSON data
|
||||
* `ToolContent` has a `tool_input` field for storing input parameters for the tool
|
||||
|
||||
### Create a ContentBlock object
|
||||
|
||||
Create a `ContentBlock` object with a list of different content types.
|
||||
|
||||
```python
|
||||
content_block = ContentBlock(
|
||||
title="Mixed Content Example",
|
||||
contents=[
|
||||
TextContent(text="This is a text content"),
|
||||
MediaContent(urls=["http://example.com/image.jpg"]),
|
||||
JSONContent(data={"key": "value"}),
|
||||
CodeContent(code="print('Hello')", language="python")
|
||||
],
|
||||
media_url=["http://example.com/additional_image.jpg"]
|
||||
)
|
||||
```
|
||||
|
||||
### Add ContentBlocks objects to a message
|
||||
|
||||
In this example, a text and a media `ContentBlock` are added to a message.
|
||||
|
||||
```python
|
||||
from langflow.schema.message import Message
|
||||
from langflow.schema.content_block import ContentBlock
|
||||
from langflow.schema.content_types import TextContent, MediaContent
|
||||
|
||||
message = Message(
|
||||
text="Main message text",
|
||||
sender="User",
|
||||
sender_name="John Doe",
|
||||
content_blocks=[
|
||||
ContentBlock(
|
||||
title="Text Block",
|
||||
contents=[
|
||||
TextContent(type="text", text="This is some text content")
|
||||
]
|
||||
),
|
||||
ContentBlock(
|
||||
title="Media Block",
|
||||
contents=[
|
||||
MediaContent(type="media", urls=["http://example.com/image.jpg"])
|
||||
]
|
||||
)
|
||||
]
|
||||
)
|
||||
```
|
||||
|
||||
## DataFrame object
|
||||
|
||||
The `DataFrame` class is a custom extension of the pandas' [DataFrame](https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html) class, specifically designed to work seamlessly with Langflow's `Data` objects. The class includes methods for converting between `DataFrame` and lists of `Data` objects.
|
||||
|
||||
A `DataFrame` object accepts various input formats, including lists of `Data` objects, dictionaries, and existing pandas DataFrames.
|
||||
|
||||
### Create a DataFrame object
|
||||
|
||||
You can create a DataFrame object using different data formats:
|
||||
|
||||
```python
|
||||
from langflow.schema import Data
|
||||
from langflow.schema.data import DataFrame
|
||||
|
||||
# From a list of Data objects
|
||||
data_list = [Data(data={"name": "John"}), Data(data={"name": "Jane"})]
|
||||
df = DataFrame(data_list)
|
||||
|
||||
# From a list of dictionaries
|
||||
dict_list = [{"name": "John"}, {"name": "Jane"}]
|
||||
df = DataFrame(dict_list)
|
||||
|
||||
# From a dictionary of lists
|
||||
data_dict = {"name": ["John", "Jane"], "age": [30, 25]}
|
||||
df = DataFrame(data_dict)
|
||||
Key Methods
|
||||
to_data_list(): Converts the DataFrame back to a list of Data objects.
|
||||
add_row(data): Adds a single row (either a Data object or a dictionary) to the DataFrame.
|
||||
add_rows(data): Adds multiple rows (list of Data objects or dictionaries) to the DataFrame.
|
||||
Usage Example
|
||||
python
|
||||
# Create a DataFrame
|
||||
df = DataFrame([Data(data={"name": "John"}), Data(data={"name": "Jane"})])
|
||||
|
||||
# Add a new row
|
||||
df = df.add_row({"name": "Alice"})
|
||||
|
||||
# Convert back to a list of Data objects
|
||||
data_list = df.to_data_list()
|
||||
|
||||
# Use pandas functionality
|
||||
filtered_df = df[df["name"].str.startswith("J")]
|
||||
```
|
||||
|
||||
To use DataFrame objects in a component input,use the DataFrameInput input type.
|
||||
|
||||
```python
|
||||
DataFrameInput(
|
||||
name="dataframe_input", display_name="DataFrame Input", info="Input for DataFrame objects.", tool_mode=True
|
||||
),
|
||||
```
|
||||
|
|
@ -1,92 +0,0 @@
|
|||
---
|
||||
title: Chat Memory
|
||||
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.
|
||||
|
||||
|
||||
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.
|
||||
|
||||
|
||||
To see and access this history of messages, Langflow features a component called [Message history](/components-helpers#message-history). It retrieves previous messages and outputs them in structured format or parsed.
|
||||
|
||||
|
||||
To learn the basics about memory in Langflow, check out the [Memory Chatbot](/tutorials-memory-chatbot) starter example.
|
||||
|
||||
|
||||
Memories can be visualized and managed directly from the **Playground**. You can edit and remove previous messages to inspect and validate the AI’s response behavior. You can remove or edit previous messages to get your models acting just right.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
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, from the playground, click the **Options** menu of any session, and then select **Message Logs**.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Session ID {#4ee86e27d1004e8288a72c633c323703}
|
||||
|
||||
|
||||
---
|
||||
|
||||
|
||||
Chat conversations store messages categorized by a `Session ID`. A single flow can host multiple session IDs, and different flows can also share the same one.
|
||||
|
||||
|
||||
The **Chat Memory** component also retrieves message histories by `Session ID`, which users can change in the component's **Controls** pane.
|
||||
|
||||
|
||||
|
||||
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**.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Store chat memory in an external database
|
||||
|
||||
Chat memory is retrieved from an external database or vector store using the [Chat Memory](/components-helpers#message-history) component.
|
||||
|
||||
Chat memory is stored to an external database or vector store using the [Store Message](/components-helpers#store-message) component.
|
||||
|
||||
The [**Chat Memories**](/components-memories) components provide access to their respective external databases **as memory**. This allows AIs to access external memory for persistence and context retention. For example, connect the **Chat Memory** component to an **AstraDBChatMemory** component to store the message history in an external Astra DB database.
|
||||
|
||||
This example stores and retrieves chat history from an [AstraDBChatMemory](/components-memories#astradbchatmemory-component) component with **Store Message** and **Chat Memory** components.
|
||||
|
||||
### Prerequisites
|
||||
|
||||
* [An OpenAI API key](https://platform.openai.com/)
|
||||
* [An Astra DB vector database](https://docs.datastax.com/en/astra-db-serverless/get-started/quickstart.html) with:
|
||||
* Application Token
|
||||
* API Endpoint
|
||||
|
||||
### Connect the chat memory component to an external database
|
||||
|
||||
1. Load the [Memory Chatbot](/tutorials-memory-chatbot) starter project.
|
||||
This starter project extends the basic prompting flow to include a chat memory component.
|
||||
2. Add the [Store Message](/components-helpers#store-message) component to the flow.
|
||||
The **Store message** component stores messages in the external database.
|
||||
3. Add the [AstraDBChatMemory Component](/components-memories#astradbchatmemory-component) to the flow.
|
||||
The **Astra DB Chat Memory** component stores and retrieves messages from **Astra DB**.
|
||||
4. Configure the **AstraDBChatMemory** component with your AstraDB instance details.
|
||||
1. In the **Astra DB Application Token** field, add your Astra token. (`AstraCS:...`)
|
||||
2. In the **API Endpoint** field, add your Astra database's endpoint. (for example, `https://12adb-bc-5378c845f05a6-e0a12-bd889b4-us-east-2.apps.astra.datastax.com`)
|
||||
5. Connect the **AstraDBChatMemory** component output to the external memory inputs of the [Message history](/components-helpers#message-history) and [Store Message](/components-helpers#store-message) components.
|
||||
6. Link the [Chat Output](/components-io#chat-output) component to the input of the [Store Message](/components-helpers#store-message) component.
|
||||
|
||||
Your completed flow should look like this:
|
||||
|
||||
|
||||
|
||||
7. In Langflow, create message traffic by running a flow.
|
||||
8. Inspect your Astra database's tables and activity.
|
||||
You will see new tables and traffic created.
|
||||
|
|
@ -1,104 +0,0 @@
|
|||
---
|
||||
title: Data & Message
|
||||
slug: /guides-data-message
|
||||
---
|
||||
|
||||
|
||||
|
||||
In Langflow, the `Data` and `Message` objects serve as structured, functional representations of data that enhance the capabilities and reliability of the platform.
|
||||
|
||||
|
||||
## The Data Object {#e0d56e463d2f483bb1b5df09d88bf309}
|
||||
|
||||
|
||||
---
|
||||
|
||||
|
||||
The `Data` object is a Pydantic model that serves as a container for storing and manipulating data. It carries `data`—a dictionary that can be accessed as attributes—and uses `text_key` to specify which key in the dictionary should be considered the primary text content.
|
||||
|
||||
|
||||
- **Main Attributes:**
|
||||
- `text_key`: Specifies the key to retrieve the primary text data.
|
||||
- `data`: A dictionary to store additional data.
|
||||
- `default_value`: default value when the `text_key` is not present in the `data` dictionary.
|
||||
|
||||
### Creating a Data Object {#3540b7e651f74b558febebbe43380660}
|
||||
|
||||
|
||||
You can create a `Data` object by directly assigning key-value pairs to it. For example:
|
||||
|
||||
|
||||
```python
|
||||
from langflow.schema import Data
|
||||
|
||||
# Creating a Data object with specified key-value pairs
|
||||
data = Data(text="my_string", bar=3, foo="another_string")
|
||||
|
||||
# Outputs:
|
||||
print(data.text) # Outputs: "my_string"
|
||||
print(data.bar) # Outputs: 3
|
||||
print(data.foo) # Outputs: "another_string"
|
||||
```
|
||||
|
||||
|
||||
The `text_key` specifies which key in the `data` dictionary should be considered the primary text content. The `default_value` provides a fallback if the `text_key` is not present.
|
||||
|
||||
|
||||
```python
|
||||
# Creating a Data object with a specific text_key and default_value
|
||||
data = Data(data={"title": "Hello, World!"}, text_key="content", default_value="No content available")
|
||||
|
||||
# Accessing the primary text using text_key and default_value
|
||||
print(data.get_text()) # Outputs: "No content available" because "content" key is not in the data dictionary
|
||||
|
||||
# Accessing data keys by calling the attribute directly
|
||||
print(data.title) # Outputs: "Hello, World!" because "title" key is in the data dictionary
|
||||
```
|
||||
|
||||
|
||||
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.
|
||||
|
||||
|
||||
## Message object attributes {#f4f17cad02a545068f407d515cbc2902}
|
||||
|
||||
|
||||
---
|
||||
|
||||
|
||||
The `Message` object extends the functionality of `Data` and includes additional attributes and methods for chat interactions.
|
||||
|
||||
|
||||
- **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
|
||||
from langflow.schema.message import Message
|
||||
|
||||
message = Message(text="Hello, AI!", sender="User", sender_name="John Doe")
|
||||
```
|
||||
|
||||
|
||||
To receive `Message` objects in a component input, you can use the `MessageInput` input type or `MessageTextInput` when the goal is to extract just the `text` field of the `Message` object.
|
||||
|
||||
|
|
@ -1,18 +0,0 @@
|
|||
---
|
||||
title: 📚 New to LLMs?
|
||||
slug: /guides-new-to-llms
|
||||
---
|
||||
|
||||
|
||||
|
||||
Large Language Models, or LLMs, are part of an exciting new world in computing.
|
||||
|
||||
|
||||
We made Langflow for anyone to create with LLMs, and hope you'll feel comfortable installing Langflow and [getting started](/get-started-quickstart).
|
||||
|
||||
|
||||
If you want to learn the basics of LLMs, prompt engineering, and AI models, Langflow recommends [promptingguide.ai](https://promptingguide.ai/), an open-source repository of prompt engineering content maintained by AI experts. PromptingGuide offers content for [beginners](https://www.promptingguide.ai/introduction/basics) and [experts](https://www.promptingguide.ai/techniques/cot), as well as the latest [research papers](https://www.promptingguide.ai/papers) and [test results](https://www.promptingguide.ai/research) fueling AI's progress.
|
||||
|
||||
|
||||
For in depth readings, we recommend [Awesome LLM Books](https://github.com/Hannibal046/Awesome-LLM?tab=readme-ov-file#llm-books), a curated list of resources for learning about LLMs and their applications.
|
||||
|
||||
|
|
@ -3,20 +3,15 @@ title: Memory Chatbot
|
|||
slug: /tutorials-memory-chatbot
|
||||
---
|
||||
|
||||
|
||||
|
||||
This flow extends the [basic prompting](/starter-projects-basic-prompting) flow to include a chat memory. This makes the AI remember previous user inputs.
|
||||
|
||||
|
||||
## Prerequisites {#a71d73e99b1543bbba827207503cf31f}
|
||||
|
||||
|
||||
---
|
||||
|
||||
- [Langflow installed and running](/get-started-installation)
|
||||
- [OpenAI API key created](https://platform.openai.com/)
|
||||
|
||||
|
||||
## Create the memory chatbot flow
|
||||
|
||||
1. From the Langflow dashboard, click **New Flow**.
|
||||
|
|
@ -25,16 +20,12 @@ This flow extends the [basic prompting](/starter-projects-basic-prompting) flo
|
|||
|
||||
|
||||
|
||||
|
||||
This flow uses the same components as the Basic Prompting one, but extends it with a **Chat Memory** component. This component retrieves previous messages and sends them to the **Prompt** component to fill a part of the **Template** with context.
|
||||
|
||||
|
||||
By clicking the template, you'll see the prompt editor like below:
|
||||
|
||||
|
||||
This gives the **OpenAI** component a memory of previous chat messages.
|
||||
|
||||
|
||||
## Run the memory chatbot flow
|
||||
|
||||
1. Open the Playground.
|
||||
|
|
@ -48,15 +39,13 @@ Check and adjust advanced parameters by opening the Advanced Settings of the **
|
|||
|
||||
|
||||
|
||||
## Use Session ID with the memory chatbot flow {#4e68c3c0750942f98c45c1c45d7ffbbe}
|
||||
|
||||
## Use Session ID with the memory chatbot flow
|
||||
|
||||
---
|
||||
|
||||
|
||||
`SessionID` is a unique identifier in Langflow that stores conversation sessions between the AI and a user. A `SessionID` is created when a conversation is initiated, and then associated with all subsequent messages during that session.
|
||||
|
||||
|
||||
In the **Memory Chatbot** flow you created, the **Chat Memory** component references past interactions by **Session ID**. You can demonstrate this by modifying the **Session ID** value to switch between conversation histories.
|
||||
|
||||
1. In the **Session ID** field of the **Chat Memory** and **Chat Input** components, add a **Session ID** value like `MySessionID`.
|
||||
|
|
@ -69,8 +58,4 @@ Every chat component in Langflow comes with a `SessionID`. It defaults to the
|
|||
|
||||
:::
|
||||
|
||||
|
||||
|
||||
|
||||
Learn more about memories in the [Chat Memory](/guides-chat-memory) section.
|
||||
|
||||
Learn more about memories in the [Memory](/components-memories) section.
|
||||
|
|
|
|||
|
|
@ -7,22 +7,17 @@ import ReactPlayer from "react-player";
|
|||
|
||||
The **Playground** is a dynamic interface designed for real-time interaction with AIs, allowing users to chat, access memories and monitor inputs and outputs. Here, users can directly prototype and their models, making adjustments and observing different outcomes.
|
||||
|
||||
|
||||
As long as you have an [Input or Output](/components-io) component working, you can open it up by clicking the **Playground** button.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
:::tip
|
||||
|
||||
Notice how the **Playground's** window arrangement changes depending on what components are being used. Langflow can be used for applications that go beyond chat-based interfaces.
|
||||
|
||||
:::
|
||||
|
||||
|
||||
## Memory Management {#821a5ee2a8a44d35b49943cba630511c}
|
||||
|
||||
## Memory Management
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -36,7 +31,7 @@ To view messages by session ID, from the Playground, click the Options menu of a
|
|||
|
||||
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).
|
||||
To learn more about chat memories in Langflow, see [Memory components](/components-memories).
|
||||
|
||||
## Use custom Session IDs for multiple user interactions
|
||||
|
||||
|
|
@ -75,4 +70,3 @@ curl -X POST \
|
|||
}
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -93,7 +93,8 @@ const config = {
|
|||
from: [
|
||||
"/whats-new-a-new-chapter-langflow",
|
||||
"/👋 Welcome-to-Langflow",
|
||||
"/getting-started-welcome-to-langflow"
|
||||
"/getting-started-welcome-to-langflow",
|
||||
"/guides-new-to-llms"
|
||||
],
|
||||
},
|
||||
{
|
||||
|
|
@ -131,6 +132,14 @@ const config = {
|
|||
to: "/configuration-global-variables",
|
||||
from: "/settings-global-variables",
|
||||
},
|
||||
{
|
||||
to: "/workspace-playground",
|
||||
from: "/guides-chat-memory",
|
||||
},
|
||||
{
|
||||
to: "/configuration-objects",
|
||||
from: "/guides-data-message",
|
||||
},
|
||||
{
|
||||
to: "/tutorials-sequential-agent",
|
||||
from: "/starter-projects-sequential-agent",
|
||||
|
|
|
|||
|
|
@ -79,16 +79,28 @@ module.exports = {
|
|||
"Configuration/configuration-cli",
|
||||
"Configuration/configuration-global-variables",
|
||||
"Configuration/environment-variables",
|
||||
"Configuration/configuration-objects",
|
||||
"Configuration/configuration-security-best-practices"
|
||||
],
|
||||
},
|
||||
{
|
||||
type: "category",
|
||||
label: "Guides",
|
||||
label: "Components",
|
||||
items: [
|
||||
"Guides/guides-chat-memory",
|
||||
"Guides/guides-data-message",
|
||||
"Guides/guides-new-to-llms",
|
||||
"Components/components-overview",
|
||||
"Components/components-agents",
|
||||
"Components/components-custom-components",
|
||||
"Components/components-data",
|
||||
"Components/components-embedding-models",
|
||||
"Components/components-helpers",
|
||||
"Components/components-io",
|
||||
"Components/components-loaders",
|
||||
"Components/components-logic",
|
||||
"Components/components-memories",
|
||||
"Components/components-models",
|
||||
"Components/components-prompts",
|
||||
"Components/components-tools",
|
||||
"Components/components-vector-stores",
|
||||
],
|
||||
},
|
||||
{
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue