Comments (11)
Here are my working versions:
langchain==0.0.350
langchain-community==0.0.2
langchain-core==0.1.0
from gpt-engineer.
It looks like there is no longer tracing_enabled in:
https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/tracers/context.py
There is a tracing_v2_enabled.
from gpt-engineer.
From the error I get it looks like this is internal to langchain
File "/usr/local/lib/python3.11/site-packages/langchain/callbacks/__init__.py", line 45, in <module>
from langchain_core.tracers.context import (
ImportError: cannot import name 'tracing_enabled' from 'langchain_core.tracers.context' (/usr/local/lib/python3.11/site-packages/langchain_core/tracers/context.py)
from gpt-engineer.
So it seems langchain-ai/langchain#15491
from gpt-engineer.
Possible solution, as suggested in above is to lock the version of core:
langchain-core==0.1.4
To fix, I changed my pyproject.toml to:
langchain = ">0.0.335, <0.1.5"
langchain-core = ">0.0.335, <0.1.5"
from gpt-engineer.
this bug was introduced in langchain 0.0349, 0.0.348 works just fine
from gpt-engineer.
Just encountered this issue and resolved it with @greenpau 's recommended fix. The key was to specify the exact versions in the requirements.txt
file prior to installing gpt-researcher
. Here are the steps I followed for a smooth setup:
Resolved Issue: Specifying Versions in requirements.txt
for GPT-Researcher Installation
Steps for Setting up GPTResearcher
-
Prepare a Fresh Folder for GPTResearcher
- Optional: Create a conda environment for isolation of dependency variables (
conda create --name gptresearcher
). This helps in minimizing any interference from other installations.
- Optional: Create a conda environment for isolation of dependency variables (
-
Navigate to the Folder in Command Prompt
- Use the command
cd /D D:/YourGPTResearcherFolder
to change your directory to the folder where you plan to clonegpt-researcher
.
- Use the command
-
Clone the GPT-Researcher Repository
- Execute
git clone https://github.com/assafelovic/gpt-researcher.git
in Command Prompt to clone the repository into your folder.
- Execute
-
Change Directory to the Cloned Repository
- Once cloned, switch to the directory using
cd gpt-researcher
.
- Once cloned, switch to the directory using
-
Edit
requirements.txt
File- Open
D:/YourGPTResearcherFolder/gpt-researcher/requirements.txt
in a text editor. - Modify the file to include the following versions:
langchain==0.0.350 langchain-community==0.0.2 langchain-core==0.1.0
- In my experience,
langchain
was already there, butcommunity
andcore
were missing.
- Open
-
Install the Requirements
- Run
pip install -r requirements.txt
in Command Prompt to install the specified dependencies.
- Run
Note: After these steps, ensure that your .env
keys (e.g., OPENAI_API_KEY
and TAVILY_API_KEY
) are set correctly. In my case, it worked well with the default settings.
This process resolved the issue for me, hope it helps others!
from gpt-engineer.
Now that you have been reading up on this and playing around @greenpau, @collinsomniac , @s1lviu @infinitelos @aguara-guazu
Are there any drawbacks with raising the langchain requirement in gpt-engineer to:
langchain = ">=0.0.350"
Are there any known compatibility losses associated with this? I suppose that may (partly?) solve this
from gpt-engineer.
@ATheorell for people like me who used the production installation method I think this is still an issue?
from gpt-engineer.
@s1lviu
I'm not sure what you mean. We haven't done anything to fix this, so unless you are using gpt-researcher and the instructions by @collinsomniac
from gpt-engineer.
I've installed the software using python -m pip install gpt-engineer
and was not sure requirements.txt can be provided with this method, as I'm not so familiar with python.
But the issue seems to be fixed now. I have run pip install --upgrade gpt_engineer langchain_core
and it disappeared.
Thanks!
from gpt-engineer.
Related Issues (20)
- Urgent - all PRs blocked because of failing tests HOT 4
- Applying diffs failing silently HOT 7
- keep getting error message when trying to run in terminal with all necessary items installed HOT 3
- The Video demo on the Main Repo is Corrupted HOT 4
- Docker build is broken HOT 30
- Add GPTE CLI argument to output system information HOT 10
- how to set gpt-4o HOT 4
- Can't run poetry install. Greenlet not supporting PEP 517 builds. HOT 1
- Azure Deployment Name Bug HOT 20
- Could not build wheels for pyarrow, which is required to install pyproject.toml-based projects HOT 6
- Implement a Unified Configuration File for Project Settings HOT 4
- Editing a project: KeyError "src/index.js" HOT 3
- Creating new project: Hang at "npm start", crash if I say "y" HOT 4
- Gemini 1.5 pro/flash HOT 6
- INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 403 Forbidden" HOT 4
- TypeError: string indices must be integers HOT 4
- Can't edit files HOT 8
- Could not resolve authentication method. HOT 7
- Improve `--sysinfo` by providing version data and env variables insights HOT 2
- using with deepseek api problem HOT 3
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 gpt-engineer.