docs: fix memory for agents (#32979)

Replaced `input_message` parameter with a directly called tuple, e.g.
`{"messages": [("user", "What is my name?")]}`

Before, the memory function wasn't working with the agent, using the
format of the input_message parameter.

Specifically, on page [Build an
Agent#adding-in-memory](https://python.langchain.com/docs/tutorials/agents/#adding-in-memory)

In the previous code, the query "What's my name?" wasn't working, as the
agent could not recall memory correctly.

<img width="860" height="679" alt="image"
src="https://github.com/user-attachments/assets/dfbca21e-ffe9-4645-a810-3be7a46d81d5"
/>
This commit is contained in:
Adam Deedman
2025-09-16 20:46:15 +01:00
committed by GitHub
parent f9605c7438
commit f8640630d8

View File

@@ -691,7 +691,7 @@
},
{
"cell_type": "code",
"execution_count": 21,
"execution_count": null,
"id": "a13462d0-2d02-4474-921e-15a1ba1fa274",
"metadata": {},
"outputs": [
@@ -709,16 +709,15 @@
}
],
"source": [
"input_message = {\"role\": \"user\", \"content\": \"Hi, I'm Bob!\"}\n",
"for step in agent_executor.stream(\n",
" {\"messages\": [input_message]}, config, stream_mode=\"values\"\n",
" {\"messages\": [(\"user\", \"Hi, I'm Bob!\")]}, config, stream_mode=\"values\"\n",
"):\n",
" step[\"messages\"][-1].pretty_print()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"execution_count": null,
"id": "56d8028b-5dbc-40b2-86f5-ed60631d86a3",
"metadata": {},
"outputs": [
@@ -736,9 +735,8 @@
}
],
"source": [
"input_message = {\"role\": \"user\", \"content\": \"What's my name?\"}\n",
"for step in agent_executor.stream(\n",
" {\"messages\": [input_message]}, config, stream_mode=\"values\"\n",
" {\"messages\": [(\"user\", \"What is my name?\")]}, config, stream_mode=\"values\"\n",
"):\n",
" step[\"messages\"][-1].pretty_print()"
]
@@ -761,7 +759,7 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": null,
"id": "24460239",
"metadata": {},
"outputs": [
@@ -782,9 +780,8 @@
"# highlight-next-line\n",
"config = {\"configurable\": {\"thread_id\": \"xyz123\"}}\n",
"\n",
"input_message = {\"role\": \"user\", \"content\": \"What's my name?\"}\n",
"for step in agent_executor.stream(\n",
" {\"messages\": [input_message]}, config, stream_mode=\"values\"\n",
" {\"messages\": [(\"user\", \"What is my name?\")]}, config, stream_mode=\"values\"\n",
"):\n",
" step[\"messages\"][-1].pretty_print()"
]