reasoning-machines / prompt-lib Goto Github PK
View Code? Open in Web Editor NEWA set of utilities for running few-shot prompting experiments on large-language models
License: MIT License
prompt-lib's People
Contributors
Stargazers
Watchers
Forkers
netzkontrast syiswell lisaterumi yanzia12138 standardgalactic nashid demongodyy evelynmitchell rxlqn drnic halfbloody siliciuss codeaudit mvandermeulen tcdsv adityasudhakarprompt-lib's Issues
Caching documentation
Add details of using --cached_timestamp for inference.
anthropic_api.py:23 -> TypeError: Anthropic.__init__() takes 1 positional argument but 2 were given
I was running through notebooks/QueryOpenAI.ipynb and I get the following error during from prompt_lib.backends import openai_api:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
[/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/QueryOpenAI.ipynb](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/QueryOpenAI.ipynb) Cell 5 line 1
----> [1](vscode-notebook-cell:/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/QueryOpenAI.ipynb#W4sZmlsZQ%3D%3D?line=0) from prompt_lib.backends import openai_api
File [~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/openai_api.py:11](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/openai_api.py:11)
[9](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/openai_api.py:9) from prompt_lib.backends.wrapper import BaseAPIWrapper
[10](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/openai_api.py:10) from prompt_lib.backends.self_hosted import OpenSourceAPIWrapper
---> [11](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/openai_api.py:11) from prompt_lib.backends.anthropic_api import AnthropicAPIWrapper
[13](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/openai_api.py:13) openai.api_key = os.getenv("OPENAI_API_KEY")
[15](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/openai_api.py:15) # check if orgainization is set
File [~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:11](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:11)
[8](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:8) from prompt_lib.backends.wrapper import BaseAPIWrapper
[10](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:10) ANTHROPIC_API_KEY = os.environ.get("ANTHROPIC_API_KEY", "Your_Default_Value")
---> [11](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:11) client = anthropic.Client(ANTHROPIC_API_KEY)
[14](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:14) class AnthropicAPIWrapper(BaseAPIWrapper):
[15](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:15) @staticmethod
[16](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:16) def _call_api(
[17](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:17) prompt: str,
ref='~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:0'>0</a>;32m (...)
[22](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:22) num_completions: int = 1,
[23](https://file+.vscode-resource.vscode-cdn.net/Users/drnic/workspace/aiagents/self-refine/prompt-lib/notebooks/~/workspace/aiagents/self-refine/prompt-lib/prompt_lib/backends/anthropic_api.py:23) ) -> dict:
TypeError: Anthropic.__init__() takes 1 positional argument but 2 were given
Add a central routing function for the APIs
Users should be able to switch between completely different backends (alpa/openai) with a parameter.
Allow generation of multiple samples
Currently the completion wrapper always returns the top 1 solution. Add an option to get the top n answers from the OpenAI API.
Create prompts using functions
Allow formatting functions to be used for creating a prompt dynamically. Currently, prompts are created either by reading from a file or by using prefixes for question/answer. This excludes use cases like https://github.com/reasoning-machines/CoCoGen
Allow loading prompts from arbitrary files
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.