[BUG] With Docker installed and started , the log was showing Dependencies not installed [GraphRAG and Nano-GraphRAG]

[Pan06da]

Description

GraphRAG dependencies not installed. Try pip install graphrag future to install. GraphRAG retriever pipeline will not work properly.
Nano-GraphRAG dependencies not installed. Try pip install nano-graphrag to install. Nano-GraphRAG retriever pipeline will not work properly.

when pip install graphrag future in bash, it will showing a version conflict with kotaeman

Reproduction steps

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Screenshots

No response

Logs

2024-12-03 21:01:32 kotaemon-1  | [nltk_data] Downloading package punkt_tab to
2024-12-03 21:01:32 kotaemon-1  | [nltk_data]     /usr/local/lib/python3.10/site-
2024-12-03 21:01:32 kotaemon-1  | [nltk_data]     packages/llama_index/core/_static/nltk_cache...
2024-12-03 21:01:33 kotaemon-1  | [nltk_data]   Unzipping tokenizers/punkt_tab.zip.
2024-12-03 21:01:42 kotaemon-1  | GraphRAG dependencies not installed. Try `pip install graphrag future` to install. GraphRAG retriever pipeline will not work properly.
2024-12-03 21:01:43 kotaemon-1  | Nano-GraphRAG dependencies not installed. Try `pip install nano-graphrag` to install. Nano-GraphRAG retriever pipeline will not work properly.
2024-12-03 21:01:43 kotaemon-1  | INFO:chromadb.telemetry.product.posthog:Anonymized telemetry enabled. See                     https://docs.trychroma.com/telemetry for more information.
2024-12-03 21:01:43 kotaemon-1  | INFO:kotaemon:posthog.capture called with args: ('be6006fd-e851-4410-8d04-2f5682659d06', 'ClientStartEvent', {'batch_size': 1, 'in_colab': False, '$process_person_profile': False, 'chroma_version': '0.5.16', 'server_context': 'None', 'hosted': False, 'chroma_api_impl': 'chromadb.api.segment.SegmentAPI', 'is_persistent': False, 'chroma_server_ssl_enabled': False, 'chroma_server_api_default_path': <APIVersion.V2: '/api/v2'>}), kwargs: {}
2024-12-03 21:01:43 kotaemon-1  | INFO:kotaemon:posthog.capture called with args: ('be6006fd-e851-4410-8d04-2f5682659d06', 'ClientCreateCollectionEvent', {'batch_size': 1, 'collection_uuid': '6ba286cf-4988-4926-924e-45189c795d6b', '$process_person_profile': False, 'chroma_version': '0.5.16', 'server_context': 'None', 'hosted': False, 'chroma_api_impl': 'chromadb.api.segment.SegmentAPI', 'is_persistent': False, 'chroma_server_ssl_enabled': False, 'chroma_server_api_default_path': <APIVersion.V2: '/api/v2'>}), kwargs: {}
2024-12-03 21:01:43 kotaemon-1  | INFO:kotaemon:posthog.capture called with args: ('be6006fd-e851-4410-8d04-2f5682659d06', 'ClientStartEvent', {'batch_size': 1, 'in_colab': False, '$process_person_profile': False, 'chroma_version': '0.5.16', 'server_context': 'None', 'hosted': False, 'chroma_api_impl': 'chromadb.api.segment.SegmentAPI', 'is_persistent': False, 'chroma_server_ssl_enabled': False, 'chroma_server_api_default_path': <APIVersion.V2: '/api/v2'>}), kwargs: {}
2024-12-03 21:01:43 kotaemon-1  | INFO:kotaemon:posthog.capture called with args: ('be6006fd-e851-4410-8d04-2f5682659d06', 'ClientCreateCollectionEvent', {'batch_size': 1, 'collection_uuid': '57df3839-4fb6-4f78-844e-732974557070', '$process_person_profile': False, 'chroma_version': '0.5.16', 'server_context': 'None', 'hosted': False, 'chroma_api_impl': 'chromadb.api.segment.SegmentAPI', 'is_persistent': False, 'chroma_server_ssl_enabled': False, 'chroma_server_api_default_path': <APIVersion.V2: '/api/v2'>}), kwargs: {}
2024-12-03 21:01:43 kotaemon-1  | INFO:kotaemon:posthog.capture called with args: ('be6006fd-e851-4410-8d04-2f5682659d06', 'ClientStartEvent', {'batch_size': 1, 'in_colab': False, '$process_person_profile': False, 'chroma_version': '0.5.16', 'server_context': 'None', 'hosted': False, 'chroma_api_impl': 'chromadb.api.segment.SegmentAPI', 'is_persistent': False, 'chroma_server_ssl_enabled': False, 'chroma_server_api_default_path': <APIVersion.V2: '/api/v2'>}), kwargs: {}
2024-12-03 21:01:43 kotaemon-1  | INFO:kotaemon:posthog.capture called with args: ('be6006fd-e851-4410-8d04-2f5682659d06', 'ClientCreateCollectionEvent', {'batch_size': 1, 'collection_uuid': '15a8f602-f923-45f8-9b53-adb416314ac3', '$process_person_profile': False, 'chroma_version': '0.5.16', 'server_context': 'None', 'hosted': False, 'chroma_api_impl': 'chromadb.api.segment.SegmentAPI', 'is_persistent': False, 'chroma_server_ssl_enabled': False, 'chroma_server_api_default_path': <APIVersion.V2: '/api/v2'>}), kwargs: {}
2024-12-03 21:01:43 kotaemon-1  | INFO:matplotlib.font_manager:generated new fontManager
2024-12-03 21:01:43 kotaemon-1  | User "admin" already exists
2024-12-03 21:01:44 kotaemon-1  | Setting up quick upload event
2024-12-03 21:01:44 kotaemon-1  | Running on local URL:  http://0.0.0.0:7860
2024-12-03 21:01:44 kotaemon-1  | INFO:httpx:HTTP Request: GET http://localhost:7860/startup-events "HTTP/1.1 200 OK"
2024-12-03 21:01:45 kotaemon-1  | INFO:botocore.credentials:Found credentials from IAM Role: AmazonLightsailInstanceRole
2024-12-03 21:01:47 kotaemon-1  | INFO:httpx:HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
2024-12-03 21:01:47 kotaemon-1  | 
2024-12-03 21:01:47 kotaemon-1  | To create a public link, set `share=True` in `launch()`.

Browsers

Chrome

OS

MacOS

Additional information

No response

[robinszeto]

Same issues in my MacOS. I used Anaconda as well.

[varunsharma27]

I solved my RAG issues by building a wrapper image, However I do think this should be a part of the original image nonetheless.

# Dockerfile
FROM ghcr.io/cinnamon/kotaemon:main-full

ENV GRADIO_SERVER_NAME 0.0.0.0
ENV GRADIO_SERVER_PORT 8080
ENV NanoGraphRAG true

RUN pip install nano-graphrag
RUN pip uninstall -y hnswlib chroma-hnswlib && pip install chroma-hnswlib

EXPOSE 8080

Build the image locally with:

docker build -t <username>/<custom-wrapper-image-name>:<tag-name> .

Remember to run the image with the variable or else RAG won't work (Ui settings are not used somehow):

docker run -e GRAPHRAG_API_KEY=my_openai_key -p 8080:8080 -it <username>/<custom-wrapper-image-name>:<tag-name>