github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-23 03:19:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

experimental: docstrings update (#18048)

Browse Source 
Added missed docstrings. Formatted docsctrings to the consistent format.
This commit is contained in:
Leonid Ganeline
2024-02-23 18:24:16 -08:00
committed by GitHub
parent 56b955fc31
commit 3f6bf852ea
61 changed files with 316 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
libs/experimental/langchain_experimental/smart_llm/__init__.py
View File

@@ -1,4 +1,23 @@
"""Generalized implementation of SmartGPT (origin: https://youtu.be/wVzuvf9D9BU)"""
"""Chain for applying self-critique using the SmartGPT workflow.
See details at https://youtu.be/wVzuvf9D9BU
The workflow performs these 3 steps:
1. **Ideate**: Pass the user prompt to an ideation LLM n_ideas times,
each result is an "idea"
2. **Critique**: Pass the ideas to a critique LLM which looks for flaws in the ideas
& picks the best one
3. **Resolve**: Pass the critique to a resolver LLM which improves upon the best idea
& outputs only the (improved version of) the best output
In total, the SmartGPT workflow will use n_ideas+2 LLM calls
Note that SmartLLMChain will only improve results (compared to a basic LLMChain),
when the underlying models have the capability for reflection, which smaller models
often don't.
Finally, a SmartLLMChain assumes that each underlying LLM outputs exactly 1 result.
"""
from langchain_experimental.smart_llm.base import SmartLLMChain

5
libs/experimental/langchain_experimental/smart_llm/base.py
View File

@@ -18,8 +18,9 @@ from langchain_experimental.pydantic_v1 import Extra, root_validator
class SmartLLMChain(Chain):
"""
Generalized implementation of SmartGPT (origin: https://youtu.be/wVzuvf9D9BU)
"""Chain for applying self-critique using the SmartGPT workflow.
See details at https://youtu.be/wVzuvf9D9BU
A SmartLLMChain is an LLMChain that instead of simply passing the prompt to the LLM
performs these 3 steps: