WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-09-27 03:55:00 +02:00
Code Issues Packages Projects Releases Wiki Activity

Pregel: Add NodeBuilder class to replace Channel.subscribe_to

Browse Source 
- For now keeping Channel.subscribe_to given it was used in docs
This commit is contained in:
Nuno Campos
2025-05-24 20:35:37 -07:00
parent 0f8f5444bc
commit 85522ec6a6
14 changed files with 494 additions and 616 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/concepts/pregel.md
+37 -49
View File
@@ -25,7 +25,7 @@ Each step consists of three phases:
Repeat until no **actors** are selected for execution, or a maximum number of steps is reached.
## Actors
## Actors
An **actor** is a `PregelNode`. It subscribes to channels, reads data from them, and writes data to them. It can be thought of as an **actor** in the Pregel algorithm. `PregelNodes` implement LangChain's Runnable interface.
@@ -39,7 +39,7 @@ Channels are used to communicate between actors (PregelNodes). Each channel has
## Examples
While most users will interact with Pregel through the [StateGraph][langgraph.graph.StateGraph] API or
While most users will interact with Pregel through the [StateGraph][langgraph.graph.StateGraph] API or
the [entrypoint][langgraph.func.entrypoint] decorator, it is possible to interact with Pregel directly.
Below are a few different examples to give you a sense of the Pregel API.
@@ -49,12 +49,12 @@ Below are a few different examples to give you a sense of the Pregel API.
```python
from langgraph.channels import EphemeralValue
from langgraph.pregel import Pregel, Channel
from langgraph.pregel import Pregel, NodeBuilder
node1 = (
Channel.subscribe_to("a")
| (lambda x: x + x)
| Channel.write_to("b")
NodeBuilder().subscribe_only("a")
.do(lambda x: x + x)
.write_to("b")
)
app = Pregel(
@@ -78,18 +78,18 @@ Below are a few different examples to give you a sense of the Pregel API.
```python
from langgraph.channels import LastValue, EphemeralValue
from langgraph.pregel import Pregel, Channel
from langgraph.pregel import Pregel, NodeBuilder
node1 = (
Channel.subscribe_to("a")
| (lambda x: x + x)
| Channel.write_to("b")
NodeBuilder().subscribe_only("a")
.do(lambda x: x + x)
.write_to("b")
)
node2 = (
Channel.subscribe_to("b")
| (lambda x: x + x)
| Channel.write_to("c")
NodeBuilder().subscribe_only("b")
.do(lambda x: x + x)
.write_to("c")
)
@@ -115,23 +115,18 @@ Below are a few different examples to give you a sense of the Pregel API.
```python
from langgraph.channels import EphemeralValue, Topic
from langgraph.pregel import Pregel, Channel
from langgraph.pregel import Pregel, NodeBuilder
node1 = (
Channel.subscribe_to("a")
| (lambda x: x + x)
| {
"b": Channel.write_to("b"),
"c": Channel.write_to("c")
}
NodeBuilder().subscribe_only("a")
.do(lambda x: x + x)
.write_to("b", "c")
)
node2 = (
Channel.subscribe_to("b")
| (lambda x: x + x)
| {
"c": Channel.write_to("c"),
}
NodeBuilder().subscribe_to("b")
.do(lambda x: x["b"] + x["b"])
.write_to("c")
)
app = Pregel(
@@ -158,24 +153,19 @@ Below are a few different examples to give you a sense of the Pregel API.
```python
from langgraph.channels import EphemeralValue, BinaryOperatorAggregate
from langgraph.pregel import Pregel, Channel
from langgraph.pregel import Pregel, NodeBuilder
node1 = (
Channel.subscribe_to("a")
| (lambda x: x + x)
| {
"b": Channel.write_to("b"),
"c": Channel.write_to("c")
}
NodeBuilder().subscribe_only("a")
.do(lambda x: x + x)
.write_to("b", "c")
)
node2 = (
Channel.subscribe_to("b")
| (lambda x: x + x)
| {
"c": Channel.write_to("c"),
}
NodeBuilder().subscribe_only("b")
.do(lambda x: x + x)
.write_to("c")
)
def reducer(current, update):
@@ -197,8 +187,7 @@ Below are a few different examples to give you a sense of the Pregel API.
app.invoke({"a": "foo"})
```
=== "Cycle"
This example demonstrates how to introduce a cycle in the graph, by having
@@ -207,12 +196,12 @@ Below are a few different examples to give you a sense of the Pregel API.
```python
from langgraph.channels import EphemeralValue
from langgraph.pregel import Pregel, Channel, ChannelWrite, ChannelWriteEntry
from langgraph.pregel import Pregel, NodeBuilder, ChannelWriteEntry
example_node = (
Channel.subscribe_to("value")
| (lambda x: x + x if len(x) < 10 else None)
| ChannelWrite(writes=[ChannelWriteEntry(channel="value", skip_none=True)])
NodeBuilder().subscribe_only("value")
.do(lambda x: x + x if len(x) < 10 else None)
.write_to(ChannelWriteEntry("value", skip_none=True))
)
app = Pregel(
@@ -235,7 +224,6 @@ Below are a few different examples to give you a sense of the Pregel API.
LangGraph provides two high-level APIs for creating a Pregel application: the [StateGraph (Graph API)](./low_level.md) and the [Functional API](functional_api.md).
=== "StateGraph (Graph API)"
The [StateGraph (Graph API)][langgraph.graph.StateGraph] is a higher-level abstraction that simplifies the creation of Pregel applications. It allows you to define a graph of nodes and edges. When you compile the graph, the StateGraph API automatically creates the Pregel application for you.
@@ -266,7 +254,7 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
builder.add_node(score_essay)
builder.add_edge(START, "write_essay")
# Compile the graph.
# Compile the graph.
# This will return a Pregel instance.
graph = builder.compile()
```
@@ -279,7 +267,7 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
You will see something like this:
```pycon
```pycon
{'__start__': <langgraph.pregel.read.PregelNode at 0x7d05e3ba1810>,
'write_essay': <langgraph.pregel.read.PregelNode at 0x7d05e3ba14d0>,
'score_essay': <langgraph.pregel.read.PregelNode at 0x7d05e3ba1710>}
@@ -310,7 +298,7 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
=== "Functional API"
In the [Functional API](functional_api.md), you can use an [`entrypoint`][langgraph.func.entrypoint] to create
a Pregel application. The `entrypoint` decorator allows you to define a function that takes input and returns output.
a Pregel application. The `entrypoint` decorator allows you to define a function that takes input and returns output.
```python
from typing import TypedDict, Optional
@@ -339,8 +327,8 @@ LangGraph provides two high-level APIs for creating a Pregel application: the [S
```
```pycon
Nodes:
Nodes:
{'write_essay': <langgraph.pregel.read.PregelNode object at 0x7d05e2f9aad0>}
Channels:
Channels:
{'__start__': <langgraph.channels.ephemeral_value.EphemeralValue object at 0x7d05e2c906c0>, '__end__': <langgraph.channels.last_value.LastValue object at 0x7d05e2c90c40>, '__previous__': <langgraph.channels.last_value.LastValue object at 0x7d05e1007280>}
```