github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-01-06 16:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs:misc fixes (#9671)

Browse Source 
Improve internal consistency in LangChain documentation
- Change occurrences of eg and eg. to e.g.
- Fix headers containing unnecessary capital letters.
- Change instances of "few shot" to "few-shot".
- Add periods to end of sentences where missing.
- Minor spelling and grammar fixes.
This commit is contained in:
seamusp
2023-08-23 22:36:54 -07:00
committed by GitHub
parent 6283f3b63c
commit 25f2c82ae8
25 changed files with 85 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/snippets/modules/chains/popular/sqlite.mdx
View File

@@ -628,7 +628,7 @@ local_chain("How many customers are there?")
</CodeOutputBlock>
Even this relatively large model will most likely fail to generate more complicated SQL by itself. However, you can log its inputs and outputs so that you can hand-correct them and use the corrected examples for few shot prompt examples later. In practice, you could log any executions of your chain that raise exceptions (as shown in the example below) or get direct user feedback in cases where the results are incorrect (but did not raise an exception).
Even this relatively large model will most likely fail to generate more complicated SQL by itself. However, you can log its inputs and outputs so that you can hand-correct them and use the corrected examples for few-shot prompt examples later. In practice, you could log any executions of your chain that raise exceptions (as shown in the example below) or get direct user feedback in cases where the results are incorrect (but did not raise an exception).
```bash
@@ -878,7 +878,7 @@ YAML_EXAMPLES = """
"""
```
Now that you have some examples (with manually corrected output SQL), you can do few shot prompt seeding the usual way:
Now that you have some examples (with manually corrected output SQL), you can do few-shot prompt seeding the usual way:
```python
@@ -925,7 +925,7 @@ few_shot_prompt = FewShotPromptTemplate(
</CodeOutputBlock>
The model should do better now with this few shot prompt, especially for inputs similar to the examples you have seeded it with.
The model should do better now with this few-shot prompt, especially for inputs similar to the examples you have seeded it with.
```python