Comments (6)
I don't think I have access to this model yet - what is the current behavior when you try to run it with promptfoo?
from promptfoo.
I think it should be added here:
promptfoo/src/providers/bedrock.ts
Line 67 in bc83295
Currently I'm getting "TypeError: Cannot read properties of undefined (reading 'params') TypeError: Cannot read properties of undefined (reading 'params') at AwsBedrockCompletionProvider.callApi"
from promptfoo.
But this'll be more complicatede - claude v2.1 supports system prompts (no "Human:" at the beggining of the prompt).
from promptfoo.
#470 solves the error at least - so you can use claude-2.1 without a system prompt.
As for supporting system prompt, what do you think is the best way? Some thoughts:
- Completely remove the logic that prepends
Human:
and appendsAssistant:
. This means that users will have to set custom prompts for Anthropic, but minimizes the amount of magic stuff that's happening - Support OpenAI-style
role
,content
JSON objects - Some other approach?
from promptfoo.
Adding Human:
Assistant:
is similar to langchain - we could try to map langchain solution to promptfoo codebase. From the other side, I agree that this "magic" isn't something I like in langchain. And we have functionality that adds prefix/suffix to the prompt in promptfoo if I remember correctly. So probably good documentation without "magic stuff" sounds reasonable.
from promptfoo.
Closing this out as this format is now legacy with Claude 3
from promptfoo.
Related Issues (20)
- Types for `promptfoo.evaluate` broken when using TS
- Add ability to bust cache from the web UI
- When Python provider raises exception, details are no longer recorded HOT 3
- Ensure percent complete accurately reflects test suite
- Migrations path incorrect in self host docker build HOT 4
- [Web UI] Image previewer not working for variables or failed tests
- CI passes despite failing build HOT 1
- python external assertion not working HOT 2
- [Web UI] Increase robustness of markdown rendering
- Specify a label with a prompt function HOT 3
- --no confirmation for cli view HOT 1
- expression to select subset of output to display in view HOT 3
- SqliteError: no such table: evals HOT 1
- Error: Unknown Amazon Bedrock model: meta.llama3-70b-instruct-v1:0 HOT 4
- Compare providers based on latency HOT 3
- Failed to fetch when attempting to log in/sign up on the web-UI after promptfoo share
- Issue when using Vertex Gemini - "undefined" JSON Error HOT 2
- bedrock:meta.llama3-70b-instruct-v1:0 - No output HOT 1
- bedrock:mistral.mixtral-8x7b-instruct-v0:1 - Validation Error HOT 1
- bedrock:cohere.command-r-plus-v1:0 - ValidationException HOT 1
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.
from promptfoo.