twelvelabs-js 0.4.11 → 0.4.12
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -2
- package/dist/README.md +2 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -246,7 +246,7 @@ Note the following about using these endpoints:
|
|
|
246
246
|
|
|
247
247
|
- The Pegasus video understanding model must be enabled for the index to which your video has been uploaded.
|
|
248
248
|
- Your prompts must be instructive or descriptive, and you can also phrase them as questions.
|
|
249
|
-
- The maximum length of a prompt is 2,000
|
|
249
|
+
- The maximum length of a prompt is 2,000 tokens.
|
|
250
250
|
|
|
251
251
|
#### Titles, topics, and hashtags
|
|
252
252
|
|
|
@@ -279,7 +279,7 @@ For a description of each field in the request and response, see the [Summaries,
|
|
|
279
279
|
To perform open-ended analysis and generate tailored text outputs based on your prompts, use the example code below, replacing the following:
|
|
280
280
|
|
|
281
281
|
- **`<YOUR_VIDEO_ID>`**: with a string representing the unique identifier of your video.
|
|
282
|
-
- **`<YOUR_PROMPT>`**: with a string that guides the model on the desired format or content. The maximum length of the prompt is 2,000
|
|
282
|
+
- **`<YOUR_PROMPT>`**: with a string that guides the model on the desired format or content. The maximum length of the prompt is 2,000 tokens. Example: "I want to generate a description for my video with the following format: Title of the video, followed by a summary in 2-3 sentences, highlighting the main topic, key events, and concluding remarks."
|
|
283
283
|
|
|
284
284
|
```js
|
|
285
285
|
const analysis = await client.analyze('<YOUR_VIDEO_ID>', '<YOUR_PROMPT>');
|
package/dist/README.md
CHANGED
|
@@ -246,7 +246,7 @@ Note the following about using these endpoints:
|
|
|
246
246
|
|
|
247
247
|
- The Pegasus video understanding model must be enabled for the index to which your video has been uploaded.
|
|
248
248
|
- Your prompts must be instructive or descriptive, and you can also phrase them as questions.
|
|
249
|
-
- The maximum length of a prompt is 2,000
|
|
249
|
+
- The maximum length of a prompt is 2,000 tokens.
|
|
250
250
|
|
|
251
251
|
#### Titles, topics, and hashtags
|
|
252
252
|
|
|
@@ -279,7 +279,7 @@ For a description of each field in the request and response, see the [Summaries,
|
|
|
279
279
|
To perform open-ended analysis and generate tailored text outputs based on your prompts, use the example code below, replacing the following:
|
|
280
280
|
|
|
281
281
|
- **`<YOUR_VIDEO_ID>`**: with a string representing the unique identifier of your video.
|
|
282
|
-
- **`<YOUR_PROMPT>`**: with a string that guides the model on the desired format or content. The maximum length of the prompt is 2,000
|
|
282
|
+
- **`<YOUR_PROMPT>`**: with a string that guides the model on the desired format or content. The maximum length of the prompt is 2,000 tokens. Example: "I want to generate a description for my video with the following format: Title of the video, followed by a summary in 2-3 sentences, highlighting the main topic, key events, and concluding remarks."
|
|
283
283
|
|
|
284
284
|
```js
|
|
285
285
|
const analysis = await client.analyze('<YOUR_VIDEO_ID>', '<YOUR_PROMPT>');
|