klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add dry_run to add() (#545)

Browse Source
This commit is contained in:
Dev Khant
2023-09-12 09:20:31 +05:30
committed by GitHub
parent 79f5a1d052
commit 7c39d9f0c1
4 changed files with 60 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/advanced/interface_types.mdx
View File

@@ -36,7 +36,7 @@ print(naval_chat_bot.chat("what did the author say about happiness?"))
#### Dry Run
Dry Run is an option in the `query` and `chat` methods that allows the user to not send their constructed prompt to the LLM, to save money. It's used for [testing](/advanced/testing#dry-run).
Dry Run is an option in the `add`, `query` and `chat` methods that allows the user to displays the data chunks and their constructed prompt which is not send to the LLM, to save money. It's used for [testing](/advanced/testing#dry-run).
### Stream Response

21
docs/advanced/testing.mdx
View File

@@ -6,11 +6,9 @@ title: '🧪 Testing'
### Dry Run
Before you consume valueable tokens, you should make sure that the embedding you have done works and that it's receiving the correct document from the database.
Before you consume valueable tokens, you should make sure that data chunks are properly created and the embedding you have done works and that it's receiving the correct document from the database.
For this you can use the `dry_run` option in your `query` or `chat` method.
Following the example above, add this to your script:
- For `query` or `chat` method, you can add this to your script:
```python
print(naval_chat_bot.query('Can you tell me who Naval Ravikant is?', dry_run=True))
@@ -26,4 +24,17 @@ A: Naval Ravikant is an Indian-American entrepreneur and investor.
_The embedding is confirmed to work as expected. It returns the right document, even if the question is asked slightly different. No prompt tokens have been consumed._
**The dry run will still consume tokens to embed your query, but it is only ~1/15 of the prompt.**
The dry run will still consume tokens to embed your query, but it is only **~1/15 of the prompt.**
- For `add` method, you can add this to your script:
```python
print(naval_chat_bot.add('https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf', dry_run=True))
'''
{'chunks': ['THE ALMANACK OF NAVAL RAVIKANT', 'GETTING RICH IS NOT JUST ABOUT LUCK;', 'HAPPINESS IS NOT JUST A TRAIT WE ARE'], 'metadata': [{'source': 'C:\\Users\\Dev\\AppData\\Local\\Temp\\tmp3g5mjoiz\\tmp.pdf', 'page': 0, 'url': 'https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf', 'data_type': 'pdf_file'}, {'source': 'C:\\Users\\Dev\\AppData\\Local\\Temp\\tmp3g5mjoiz\\tmp.pdf', 'page': 2, 'url': 'https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf', 'data_type': 'pdf_file'}, {'source': 'C:\\Users\\Dev\\AppData\\Local\\Temp\\tmp3g5mjoiz\\tmp.pdf', 'page': 2, 'url': 'https://navalmanack.s3.amazonaws.com/Eric-Jorgenson_The-Almanack-of-Naval-Ravikant_Final.pdf', 'data_type': 'pdf_file'}], 'count': 7358, 'type': <DataType.PDF_FILE: 'pdf_file'>}
# less items to show for readability
'''
```