WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-09-10 11:47:51 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: reorganize API refs (#1884)

Browse Source
This commit is contained in:
Vadym Barda
2024-09-27 18:12:12 -04:00
committed by GitHub
parent 98f5df4f6f
commit 03be3b6567
18 changed files with 118 additions and 222 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/reference/channels.md
+15
View File
@@ -0,0 +1,15 @@
# Channels
::: langgraph.channels.base
options:
members:
- BaseChannel
::: langgraph.channels
options:
members:
- Topic
- LastValue
- EphemeralValue
- BinaryOperatorAggregate
- AnyValue
docs/docs/reference/checkpoints.md
+20 -53
View File
@@ -1,62 +1,29 @@
# Checkpointers
You can [compile][langgraph.graph.MessageGraph.compile] any LangGraph workflow with a [Checkpointer][basecheckpointsaver] to give your agent "memory" by persisting its state. This permits things like:
::: langgraph.checkpoint.base
options:
members:
- CheckpointMetadata
- Checkpoint
- BaseCheckpointSaver
- create_checkpoint
- Remembering things across multiple interactions
- Interrupting to wait for user input
- Resilience for long-running, error-prone agents
- Time travel retry and branch from a previous checkpoint
::: langgraph.checkpoint.serde.base
options:
members:
- SerializerProtocol
Key checkpointer interfaces and primitives are defined in [`langgraph_checkpoint`](https://github.com/langchain-ai/langgraph/tree/main/libs/checkpoint) library. Additional checkpointer implementations are also available as installable libraries:
* [`langgraph-checkpoint-sqlite`](https://github.com/langchain-ai/langgraph/tree/main/libs/checkpoint-sqlite): An implementation of LangGraph checkpointer that uses SQLite database. Ideal for experimentation and local workflows.
* [`langgraph-checkpoint-postgres`](https://github.com/langchain-ai/langgraph/tree/main/libs/checkpoint-postgres): An advanced checkpointer that uses Postgres database, used in LangGraph Cloud. Ideal for using in production.
::: langgraph.checkpoint.serde.jsonplus
options:
members:
- JsonPlusSerializer
### Checkpoint
::: langgraph.checkpoint.memory
::: langgraph.checkpoint.base.Checkpoint
::: langgraph.checkpoint.sqlite
### CheckpointMetadata
::: langgraph.checkpoint.sqlite.aio
::: langgraph.checkpoint.base.CheckpointMetadata
::: langgraph.checkpoint.postgres
### BaseCheckpointSaver
::: langgraph.checkpoint.base.BaseCheckpointSaver
## Serialization / deserialization
### SerializerProtocol
::: langgraph.checkpoint.base.SerializerProtocol
### JsonPlusSerializer
::: langgraph.checkpoint.serde.jsonplus.JsonPlusSerializer
## Checkpointer Implementations
LangGraph also natively provides the following checkpoint implementations.
### MemorySaver
::: langgraph.checkpoint.memory.MemorySaver
### AsyncSqliteSaver
::: langgraph.checkpoint.sqlite.aio.AsyncSqliteSaver
### SqliteSaver
::: langgraph.checkpoint.sqlite.SqliteSaver
### AsyncPostgresSaver
::: langgraph.checkpoint.postgres.aio.AsyncPostgresSaver
### PostgresSaver
::: langgraph.checkpoint.postgres.PostgresSaver
handler: python
handler: python
::: langgraph.checkpoint.postgres.aio
docs/docs/reference/constants.md
+6
View File
@@ -0,0 +1,6 @@
::: langgraph.constants
options:
members:
- TAG_HIDDEN
- START
- END
docs/docs/reference/errors.md
-3
View File
@@ -1,6 +1,3 @@
# Errors
While you may not want to see them, informative errors help you design better workflows.
Below are the LangGraph-specific errors and what they mean.
::: langgraph.errors
docs/docs/reference/graphs.md
+14 -76
View File
@@ -1,80 +1,18 @@
# Graph Definitions
Graphs are the core abstraction of LangGraph. Each [StateGraph](#stategraph) implementation is used to create graph workflows. Once compiled, you can run the [CompiledGraph](#compiledgraph) to run the application.
::: langgraph.graph.graph
options:
members:
- Graph
- CompiledGraph
## StateGraph
::: langgraph.graph.state
options:
members:
- StateGraph
- CompiledStateGraph
```python
from langgraph.graph import StateGraph
from typing_extensions import TypedDict
class MyState(TypedDict)
...
graph = StateGraph(MyState)
```
::: langgraph.graph.StateGraph
handler: python
## MessageGraph
::: langgraph.graph.message.MessageGraph
## `add_messages`
::: langgraph.graph.message.add_messages
## CompiledGraph
::: langgraph.graph.graph.CompiledGraph
## StreamMode
::: langgraph.types.StreamMode
## Constants
The following constants and classes are used to help control graph execution.
## START
START is a string constant (`"__start__"`) that serves as a "virtual" node in the graph.
Adding an edge (or conditional edges) from `START` to node one or more nodes in your graph
will direct the graph to begin execution there.
```python
from langgraph.graph import START
...
builder.add_edge(START, "my_node")
# Or to add a conditional starting point
builder.add_conditional_edges(START, my_condition)
```
## END
END is a string constant (`"__end__"`) that serves as a "virtual" node in the graph. Adding
an edge (or conditional edges) from one or more nodes in your graph to the `END` "node" will
direct the graph to cease execution as soon as it reaches this point.
```python
from langgraph.graph import END
...
builder.add_edge("my_node", END) # Stop any time my_node completes
# Or to conditionally terminate
def my_condition(state):
if state["should_stop"]:
return END
return "my_node"
builder.add_conditional_edges("my_node", my_condition)
```
## Send
::: langgraph.types.Send
## Interrupt
::: langgraph.types.Interrupt
## RetryPolicy
::: langgraph.types.RetryPolicy
::: langgraph.graph.message
options:
members:
- add_messages
docs/docs/reference/prebuilt.md
+14 -63
View File
@@ -1,67 +1,18 @@
# Prebuilt
## create_react_agent
::: langgraph.prebuilt.chat_agent_executor
options:
members:
- create_react_agent
```python
from langgraph.prebuilt import create_react_agent
```
::: langgraph.prebuilt.tool_node
options:
members:
- ToolNode
- InjectedState
- tools_condition
::: langgraph.prebuilt.create_react_agent
## ToolNode
```python
from langgraph.prebuilt import ToolNode
```
::: langgraph.prebuilt.ToolNode
handler: python
## ToolExecutor
```python
from langgraph.prebuilt import ToolExecutor
```
::: langgraph.prebuilt.ToolExecutor
handler: python
## ToolInvocation
```python
from langgraph.prebuilt import ToolInvocation
```
::: langgraph.prebuilt.ToolInvocation
handler: python
heading_level: 4
## `tools_condition`
```python
from langgraph.prebuilt import tools_condition
```
::: langgraph.prebuilt.tools_condition
## ValidationNode
```python
from langgraph.prebuilt import ValidationNode
```
::: langgraph.prebuilt.ValidationNode
## InjectedState
```python
from langgraph.prebuilt import InjectedState
```
::: langgraph.prebuilt.InjectedState
handler: python
::: langgraph.prebuilt.tool_validator
options:
members:
- ValidationNode
docs/docs/reference/types.md
+15
View File
@@ -0,0 +1,15 @@
# Types
::: langgraph.types
options:
members:
- All
- StreamMode
- StreamWriter
- RetryPolicy
- CachePolicy
- Interrupt
- PregelTask
- PregelExecutableTask
- StateSnapshot
- Send