mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-09-06 17:57:49 +02:00
docs: how-to fix some issues (#1983)
Fixes some issues introduced while updating how-to docs
This commit is contained in:
Eugene Yurtsev
@@ -18,8 +18,8 @@
|
||||
" </a>\n",
|
||||
" </li>\n",
|
||||
" <li>\n",
|
||||
" <a href=\"https://langchain-ai.github.io/langgraph/concepts/high_level/\">\n",
|
||||
" LangGraph Concepts\n",
|
||||
" <a href=\"https://langchain-ai.github.io/langgraph/concepts/low_level/\">\n",
|
||||
" LangGraph Glossary\n",
|
||||
" </a>\n",
|
||||
" </li>\n",
|
||||
" <li>\n",
|
||||
|
||||
@@ -18,15 +18,24 @@
|
||||
" This guide assumes familiarity with the following:\n",
|
||||
" <ul>\n",
|
||||
" <li>\n",
|
||||
" <a href=\"https://langchain-ai.github.io/langgraph/concepts/high_level/\">\n",
|
||||
" LangGraph Concepts\n",
|
||||
" <a href=\"https://langchain-ai.github.io/langgraph/concepts/low_level/#nodes\">\n",
|
||||
" Node\n",
|
||||
" </a>\n",
|
||||
" </li>\n",
|
||||
" <li>\n",
|
||||
" <a href=\"https://langchain-ai.github.io/langgraph/concepts/low_level/#edges\">\n",
|
||||
" Edge\n",
|
||||
" </a>\n",
|
||||
" </li> \n",
|
||||
" <li>\n",
|
||||
" <a href=\"https://langchain-ai.github.io/langgraph/concepts/low_level/#reducers\">\n",
|
||||
" Reducer\n",
|
||||
" </a>\n",
|
||||
" </li>\n",
|
||||
" </ul>\n",
|
||||
" </p>\n",
|
||||
"</div> \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Parallel execution of nodes is essential to speed up overall graph operation. LangGraph offers native support for parallel execution of nodes, which can significantly enhance the performance of graph-based workflows. This parallelization is achieved through fan-out and fan-in mechanisms, utilizing both standard edges and [conditional_edges](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.MessageGraph.add_conditional_edges). Below are some examples showing how to add create branching dataflows that work for you. \n",
|
||||
"\n",
|
||||
""
|
||||
|
||||
@@ -151,14 +151,6 @@
|
||||
"print()\n",
|
||||
"print(f\"Output of graph invocation: {response}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4ce80b5c-73cc-4f78-9d14-26c4ba46f478",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
||||
@@ -30,9 +30,16 @@
|
||||
"\n",
|
||||
"This reference implementation shows how to use MongoDB as the backend for persisting checkpoint state. Make sure that you have MongoDB running on port `27017` for going through this guide.\n",
|
||||
"\n",
|
||||
"NOTE: this is just an reference implementation. You can implement your own checkpointer using a different database or modify this one as long as it conforms to the `BaseCheckpointSaver` interface.\n",
|
||||
"<div class=\"admonition tip\">\n",
|
||||
" <p class=\"admonition-title\">Note</p>\n",
|
||||
" <p>\n",
|
||||
" This is a **reference** implementation. You can implement your own checkpointer using a different database or modify this one as long as it conforms to the <a href=\"https://langchain-ai.github.io/langgraph/reference/checkpoints/#langgraph.checkpoint.base.BaseCheckpointSaver\">BaseCheckpointSaver</a> interface.\n",
|
||||
" </p>\n",
|
||||
"</div>\n",
|
||||
"\n",
|
||||
"For demonstration purposes we add persistence to the [pre-built create react agent](https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent), but you can add a checkpointer to any custom graph that you build.\n",
|
||||
"\n",
|
||||
"## TLDR\n",
|
||||
" \n",
|
||||
"```python\n",
|
||||
"from langgraph.graph import StateGraph\n",
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
" <a href=\"https://langchain-ai.github.io/langgraph/concepts/persistence/\">\n",
|
||||
" Persistence\n",
|
||||
" </a>\n",
|
||||
" </li> \n",
|
||||
" </li>\n",
|
||||
" <li>\n",
|
||||
" <a href=\"https://redis.io/\">\n",
|
||||
" Redis\n",
|
||||
@@ -30,8 +30,12 @@
|
||||
"\n",
|
||||
"This reference implementation shows how to use Redis as the backend for persisting checkpoint state. Make sure that you have Redis running on port `6379` for going through this guide.\n",
|
||||
"\n",
|
||||
"NOTE: this is just an reference implementation. You can implement your own checkpointer using a different database or modify this one as long as it conforms to the `BaseCheckpointSaver` interface.\n",
|
||||
"\n",
|
||||
"<div class=\"admonition tip\">\n",
|
||||
" <p class=\"admonition-title\">Note</p>\n",
|
||||
" <p>\n",
|
||||
" This is a **reference** implementation. You can implement your own checkpointer using a different database or modify this one as long as it conforms to the <a href=\"https://langchain-ai.github.io/langgraph/reference/checkpoints/#langgraph.checkpoint.base.BaseCheckpointSaver\">BaseCheckpointSaver</a> interface.\n",
|
||||
" </p>\n",
|
||||
"</div>\n",
|
||||
"\n",
|
||||
"For demonstration purposes we add persistence to the [pre-built create react agent](https://langchain-ai.github.io/langgraph/reference/prebuilt/#langgraph.prebuilt.chat_agent_executor.create_react_agent), but you can add a checkpointer to any custom graph that you build.\n",
|
||||
"\n",
|
||||
@@ -41,7 +45,7 @@
|
||||
"\n",
|
||||
"builder = StateGraph(....)\n",
|
||||
"# ... define the graph\n",
|
||||
"checkpointer = # mongodb checkpointer (see examples below)\n",
|
||||
"checkpointer = # redis checkpointer (see examples below)\n",
|
||||
"graph = builder.compile(checkpointer=checkpointer)\n",
|
||||
"...\n",
|
||||
"```"
|
||||
@@ -1037,7 +1041,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.9"
|
||||
"version": "3.11.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -25,7 +25,7 @@
|
||||
" <li>\n",
|
||||
" <a href=\"https://github.com/pydantic/pydantic\">\n",
|
||||
" Pydantic\n",
|
||||
" </a> -- this is a very popular Python library for run time validation.\n",
|
||||
" </a>: this is a popular Python library for run time validation.\n",
|
||||
" </li>\n",
|
||||
" </ul>\n",
|
||||
" </p>\n",
|
||||
@@ -41,10 +41,20 @@
|
||||
"<div class=\"admonition note\">\n",
|
||||
" <p class=\"admonition-title\">Known Limitations</p>\n",
|
||||
" <p>\n",
|
||||
" * This notebook uses Pydantic v2 <code>BaseModel</code>, which requires <code>langchain-core >= 0.3</code>. Using <code>langchain-core < 0.3</code> will result in errors due to mixing of Pydantic v1 and v2 <code>BaseModels</code>.\n",
|
||||
" * Currently, the `output` of the graph will **NOT** be an instance of a pydantic model.\n",
|
||||
" * Run-time validation only occurs on **inputs** into nodes, not on the outputs.\n",
|
||||
" * The validation error trace from pydantic does not show which node the error arises in.\n",
|
||||
" <ul>\n",
|
||||
" <li>\n",
|
||||
" This notebook uses Pydantic v2 <code>BaseModel</code>, which requires <code>langchain-core >= 0.3</code>. Using <code>langchain-core < 0.3</code> will result in errors due to mixing of Pydantic v1 and v2 <code>BaseModels</code>. \n",
|
||||
" </li> \n",
|
||||
" <li>\n",
|
||||
" Currently, the `output` of the graph will **NOT** be an instance of a pydantic model.\n",
|
||||
" </li>\n",
|
||||
" <li>\n",
|
||||
" Run-time validation only occurs on **inputs** into nodes, not on the outputs.\n",
|
||||
" </li>\n",
|
||||
" <li>\n",
|
||||
" The validation error trace from pydantic does not show which node the error arises in.\n",
|
||||
" </li>\n",
|
||||
" </ul>\n",
|
||||
" </p>\n",
|
||||
"</div>"
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user