fix(docs): update VISION_LLM_MODEL reference from gpt-4v to gpt-4o in README
Some checks are pending
Build and Push Docker Images / test (push) Waiting to run
Build and Push Docker Images / build-amd64 (push) Blocked by required conditions
Build and Push Docker Images / build-arm64 (push) Blocked by required conditions
Build and Push Docker Images / merge-manifests (push) Blocked by required conditions
Build and Push Docker Images / E2E Tests (push) Blocked by required conditions

This commit is contained in:
Dominik Schröter 2025-03-13 23:33:36 +01:00
parent 569637389a
commit 67001d0ab1

View file

@ -120,7 +120,7 @@ services:
# Option 1: LLM-based OCR # Option 1: LLM-based OCR
OCR_PROVIDER: "llm" # Default OCR provider OCR_PROVIDER: "llm" # Default OCR provider
VISION_LLM_PROVIDER: "ollama" # openai or ollama VISION_LLM_PROVIDER: "ollama" # openai or ollama
VISION_LLM_MODEL: "minicpm-v" # minicpm-v (ollama) or gpt-4v (openai) VISION_LLM_MODEL: "minicpm-v" # minicpm-v (ollama) or gpt-4o (openai)
OLLAMA_HOST: "http://host.docker.internal:11434" # If using Ollama OLLAMA_HOST: "http://host.docker.internal:11434" # If using Ollama
# Option 2: Google Document AI # Option 2: Google Document AI
@ -191,7 +191,7 @@ paperless-gpt supports three different OCR providers, each with unique strengths
### 1. LLM-based OCR (Default) ### 1. LLM-based OCR (Default)
- **Key Features**: - **Key Features**:
- Uses vision-capable LLMs like GPT-4V or MiniCPM-V - Uses vision-capable LLMs like gpt-4o or MiniCPM-V
- High accuracy with complex layouts and difficult scans - High accuracy with complex layouts and difficult scans
- Context-aware text recognition - Context-aware text recognition
- Self-correcting capabilities for OCR errors - Self-correcting capabilities for OCR errors
@ -203,7 +203,7 @@ paperless-gpt supports three different OCR providers, each with unique strengths
```yaml ```yaml
OCR_PROVIDER: "llm" OCR_PROVIDER: "llm"
VISION_LLM_PROVIDER: "openai" # or "ollama" VISION_LLM_PROVIDER: "openai" # or "ollama"
VISION_LLM_MODEL: "gpt-4v" # or "minicpm-v" VISION_LLM_MODEL: "gpt-4o" # or "minicpm-v"
``` ```
### 2. Azure Document Intelligence ### 2. Azure Document Intelligence