[go: up one dir, main page]
Skip to content

Commit

Permalink
minor docs mistakes
Browse files Browse the repository at this point in the history
  • Loading branch information
@kritinv
kritinv committed Sep 26, 2024
1 parent ea1a5a0 commit b13d7dd
Showing 1 changed file with 3 additions and 4 deletions.
7 changes: 3 additions & 4 deletions docs/docs/evaluation-datasets-synthetic-data.mdx
View file
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,6 @@ from deepeval.synthesizer import Synthesizer
synthesizer = Synthesizer()
synthesizer.generate_goldens_from_docs(
document_paths=['example.txt', 'example.docx', 'example.pdf'],
max_goldens_per_document=2
)
```

Expand Down Expand Up @@ -92,7 +91,7 @@ For those interested in what these evolutions mean, you can [read this article h
The `generate_goldens_from_docs` method employs a token-based text splitter to manage document chunking, meaning the `chunk_size` and `chunk_overlap` parameters do not guarantee exact context sizes. This approach is designed to ensure **meaningful and coherent context extraction**, but might lead to variations in the expected size of each `context`.

:::caution
The synthesizer will raise an error if `chunk_size` is too large for `max_goldens_per_document`, and suggest **the appropriate number of chunks** to use.
The synthesizer will raise an error if `chunk_size` is too large for required `max_contexts_per_document`, and suggest **the appropriate number of chunks** to use.
:::

### 2. Generating From Provided Contexts
Expand Down Expand Up @@ -199,8 +198,8 @@ Here’s an example of what the resulting DataFrame might look like:

| input | actual_output | expected_output | context | retrieval_context | n_chunks_per_context | context_length | context_quality | synthetic_input_quality | evolutions | source_file |
| ---------------------------------------------- | ------------- | --------------- | --------------------------------------------------------------------- | ----------------- | -------------------- | -------------- | --------------- | ----------------------- | ---------- | ----------- |
| Who wrote the novel "1984"? | None | George Orwell | ["1984 is a dystopian novel published in 1949 by George Orwell."] | None | 1 | 60 | None | file1.txt | None | file1.txt |
| What is the boiling point of water in Celsius? | None | 100°C | ["Water boils at 100°C (212°F) under standard atmospheric pressure."] | None | 1 | 55 | None | file2.txt | None | file2.txt |
| Who wrote the novel "1984"? | None | George Orwell | ["1984 is a dystopian novel published in 1949 by George Orwell."] | None | 1 | 60 | 0.5 | 0.6 | None | file1.txt |
| What is the boiling point of water in Celsius? | None | 100°C | ["Water boils at 100°C (212°F) under standard atmospheric pressure."] | None | 1 | 55 | 0.4 | 0.9 | None | file2.txt |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |

## Saving Generated Goldens
Expand Down

0 comments on commit b13d7dd

Please sign in to comment.