Skip to content

Commit 5cf69c2

Browse files
doc: fixing typos in various files (#1149)
* doc: fixing typos in various files * Update llm-agents.md * Update part4.md * Update part4.md * Update computer-use.md reverting changes to moved file --------- Co-authored-by: Joe Fernandez <joefernandez@users.noreply.github.com>
1 parent c75cf73 commit 5cf69c2

File tree

3 files changed

+3
-3
lines changed

3 files changed

+3
-3
lines changed

docs/context/compaction.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,7 @@ increases size of the second summary compression, and each summary afterwards,
5050
as shown in Figure 1.
5151

5252
![Context compaction example illustration](/adk-docs/assets/context-compaction.svg)
53-
**Figure 1.** Ilustration of event compaction configuration with a interval of 3
53+
**Figure 1.** Illustration of event compaction configuration with an interval of 3
5454
and overlap of 1.
5555

5656
With this example configuration, the context compression tasks happen as follows:

docs/get-started/streaming/quickstart-streaming.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -47,7 +47,7 @@ adk-streaming/ # Project folder
4747

4848
Copy-paste the following code block into the `agent.py` file.
4949

50-
For `model`, please double check the model ID as described earlier in the [Models section](#supported-models).
50+
For `model`, please double-check the model ID as described earlier in the [Models section](#supported-models).
5151

5252
```py
5353
from google.adk.agents import Agent

docs/safety/index.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -537,7 +537,7 @@ Code execution is a special tool that has extra security implications: sandboxin
537537

538538
Google and the ADK provide several options for safe code execution. [Vertex Gemini Enterprise API code execution feature](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/code-execution-api) enables agents to take advantage of sandboxed code execution server-side by enabling the tool\_execution tool. For code performing data analysis, you can use the [Code Executor](/adk-docs/tools/gemini-api/code-execution/) tool in ADK to call the [Vertex Code Interpreter Extension](https://cloud.google.com/vertex-ai/generative-ai/docs/extensions/code-interpreter).
539539

540-
If none of these options satisfy your requirements, you can build your own code executor using the building blocks provided by the ADK. We recommend creating execution environments that are hermetic: no network connections and API calls permitted to avoid uncontrolled data exfiltration; and full clean up of data across execution to not create cross-user exfiltration concerns.
540+
If none of these options satisfy your requirements, you can build your own code executor using the building blocks provided by the ADK. We recommend creating execution environments that are hermetic: no network connections and API calls permitted to avoid uncontrolled data exfiltration; and full cleanup of data across execution to not create cross-user exfiltration concerns.
541541

542542
### Evaluations
543543

0 commit comments

Comments
 (0)