Comments (5)
@justinqcai this happens when you already have a PgVector volume meaning the init db couldn't create the ai
role. No worries the easiest path for us is to use a different name for the PgVector database. Update your cookbook/knowledge/resources.py
file to:
from phi.docker.app.postgres import PgVectorDb
from phi.docker.resources import DockerResources
# -*- PgVector running on port 5532:5432
vector_db = PgVectorDb(
name="knowledge-db",
pg_user="ai",
pg_password="ai",
pg_database="ai",
host_port=5532,
)
# -*- DockerResources
dev_docker_resources = DockerResources(apps=[vector_db])
Then run phi start cookbook/knowledge/resources.py -y
and it should work
I've update the resources file in the cookbook as well so you can just pull from main to get the new code.
Let me know if you still face an issue :)
from phidata.
Awesome, thanks! It looks like the resources file in /cookbook/rag and the whole folder in general looks to be a duplicate, just wanted to bring that up as well before closing this thread out. Probably worth updating that resources file as well or simply removing the duplicate folder
from phidata.
@justinqcai that is correct, the duplicates are intentional as users usually look for RAG/PDF cookbooks which are the duplicates but make it easier for users to search. im open to suggestions here :)
from phidata.
@ashpreetbedi That makes sense, in that case my only suggestion would be to update that file with the same changes you made here so users can run the RAG cookbook properly! Thanks Ash
from phidata.
Very good idea @justinqcai, will do that
from phidata.
Related Issues (20)
- /cookbook/llms/ollama "Method not allowed" from image.py and tool_call.py
- phidata/cookbook/examples/research example error
- Gemini sometimes returns a list index error while streaming HOT 3
- Groq Llama 3 models function calling fails HOT 5
- Azure OpenAI using print_response streaming error HOT 3
- Ollama: Wrong user message repeated in prompt as the latest user message
- How to calculate the LLM tokens usage when do an assistant's run? HOT 3
- Inconsistency in output_model paramter. HOT 2
- Can I integrate Tavaily Search Tool there? HOT 1
- Why the same python tools run many times? HOT 2
- Error after 4 to 5 queries input HOT 2
- Can the toolkits "PythonTools" being reusable? HOT 3
- Why the `PythonTools` will always being called? HOT 2
- Tools and Function Calls Not Working in OpenAILike Mode HOT 4
- Question about PDF AI at https://pdf.aidev.run/ HOT 1
- AttributeError: 'NoneType' object has no attribute 'model_dump' HOT 2
- How to set `debug_mode` in runtime when using Assiatant? HOT 1
- A feature of filters is missing from assistant
- Cannot use non-vectorstore retrievers in `LangChainKnowledgeBase`
- Workspace supports custom stages
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 phidata.