mirror of
https://github.com/hwchase17/langchain.git
synced 2025-07-01 19:03:25 +00:00
docs: fix minor typo + add wikipedia package installation part in human_input_llm.ipynb (#5118)
# Fix typo + add wikipedia package installation part in human_input_llm.ipynb This PR 1. Fixes typo ("the the human input LLM"), 2. Addes wikipedia package installation part (in accordance with `WikipediaQueryRun` [documentation](https://python.langchain.com/en/latest/modules/agents/tools/examples/wikipedia.html)) in `human_input_llm.ipynb` (`docs/modules/models/llms/examples/human_input_llm.ipynb`)
This commit is contained in:
parent
753f4cfc26
commit
7a75bb2121
@ -5,7 +5,7 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# How (and why) to use the the human input LLM\n",
|
||||
"# How (and why) to use the human input LLM\n",
|
||||
"\n",
|
||||
"Similar to the fake LLM, LangChain provides a pseudo LLM class that can be used for testing, debugging, or educational purposes. This allows you to mock out calls to the LLM and simulate how a human would respond if they received the prompts.\n",
|
||||
"\n",
|
||||
@ -34,6 +34,23 @@
|
||||
"from langchain.agents import AgentType"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Since we will use the `WikipediaQueryRun` tool in this notebook, you might need to install the `wikipedia` package if you haven't done so already."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install wikipedia"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
@ -217,7 +234,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.3"
|
||||
"version": "3.10.9"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
|
Loading…
Reference in New Issue
Block a user