docs: run how-to guides in CI (#27615)

Add how-to guides to [Run notebooks
job](https://github.com/langchain-ai/langchain/actions/workflows/run_notebooks.yml)
and fix existing notebooks.

- As with tutorials, cassettes must be updated when HTTP calls in guides
change (by running existing
[script](https://github.com/langchain-ai/langchain/blob/master/docs/scripts/update_cassettes.sh)).
- Cassettes now total ~62mb over 474 files.
- `docs/scripts/prepare_notebooks_for_ci.py` lists a number of notebooks
that do not run (e.g., due to requiring additional infra, slowness,
requiring `input()`, etc.).

docs/scripts/update_cassettes.sh

@@ -1,5 +1,24 @@
 #!/bin/bash
 
+# Use this script to update cassettes for a notebook. The script does the following:
+#
+# 1. Delete existing cassettes for the specified notebook
+# 2. Pre-download and cache nltk and tiktoken files
+# 3. Modify the notebook to generate cassettes for each cell.
+# 4. Execute the notebook.
+#
+# Important: make sure the notebook is in a clean state, with any desired changes
+# staged or committed. The script will modify the notebook in place, and these
+# modifications should be discarded after the cassettes are generated.
+#
+# Usage:
+# In monorepo env, `poetry install --with dev,test`
+# `./docs/scripts/update_cassettes.sh path/to/notebook`
+# e.g., `./docs/scripts/update_cassettes.sh docs/docs/how_to/tool_choice.ipynb`
+#
+# Make sure to set any env vars required by the notebook.
+
+
 # Get the working directory from the input argument, default to 'all' if not provided
 WORKING_DIRECTORY=${1:-all}
 
@@ -21,8 +40,8 @@ delete_cassettes() {
 delete_cassettes "$WORKING_DIRECTORY"
 
 # Pre-download tiktoken files
-echo "Pre-downloading tiktoken files..."
-poetry run python docs/scripts/download_tiktoken.py
+echo "Pre-downloading nltk and tiktoken files..."
+poetry run python docs/scripts/cache_data.py
 
 # Prepare notebooks
 echo "Preparing notebooks for CI..."