You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The first example loads an audio (MP3) file containing Mozart's Requiem in D Minor and prompts Gemini to return a single array of strings, with each string being an instrument from the song.
From a quick Google search, we see the song was composed using the following instruments:
35
35
36
36
```txt
37
37
The Requiem is scored for 2 basset horns in F, 2 bassoons, 2 trumpets in D, 3 trombones (alto, tenor, and bass),
38
-
timpani (2 drums), violins, viola, and basso continuo (cello, double bass, and organ).
38
+
timpani (2 drums), violins, viola, and basso continuo (cello, double bass, and organ).
39
39
```
40
40
41
41
Gemini did pretty well here! For music not being it's primary focus, it was able to identify a few of the instruments used in the song, and didn't hallucinate any!
@@ -45,8 +45,8 @@ Gemini did pretty well here! For music not being it's primary focus, it was able
45
45
This example takes a screen recording of a [LangChain YouTube video on datasets and testing in LangSmith](https://www.youtube.com/watch?v=N9hjO-Uy1Vo) sped up to 1.5x speed.
46
46
It is then converted to `base64` format like the example above, and sent to Gemini with a prompt asking for structured output of tasks I can do to followup on the video.
Here it also did well, giving me three tasks, just like I requested. It also responded with a valid JSON array, even though no function calling was used!
52
+
Here it also did well, giving me three tasks, just like I requested. It also responded with a valid JSON array, even though no function calling was used!
"Learn how to use the LangSmith SDK to create, edit, and manage datasets programmatically, allowing for automation and integration with other tools.",
53
56
"Investigate the versioning capabilities of LangSmith datasets and understand how to track changes, revert to previous versions, and collaborate effectively on dataset development."
0 commit comments