+ add info about pull minicpm-v

+ load proper env in makefile

Author: choinek

.env.localhost.example

@@ -1,6 +1,7 @@
 #APP_ENV=production # sets the app into prod mode, othervise dev mode with auto-reload on code changes
 REDIS_CACHE_URL=redis://localhost:6379/1
 LLAMA_VISION_PROMPT="You are OCR. Convert image to markdown."
+DISABLE_LOCAL_OLLAMA=0
 
 # CLI settings
 OCR_URL=http://localhost:8000/ocr/upload

Makefile

@@ -3,6 +3,13 @@ SHELL := /bin/bash
 export DISABLE_VENV ?= 0
 export DISABLE_LOCAL_OLLAMA ?= 0
 
+define load_env
+	@if [ -f $(1) ]; then \
+		echo "Loading environment from $(1)"; \
+		set -o allexport; source $(1); set +o allexport; \
+	fi
+endef
+
 .PHONY: help
 help:
 	@echo "Available commands:"
@@ -81,6 +88,7 @@ install-requirements:
 
 .PHONY: run
 run:
+	@$(call load_env,.env.localhost)
 	@echo "Starting the local application server..."; \
 	DISABLE_VENV=$(DISABLE_VENV) DISABLE_LOCAL_OLLAMA=$(DISABLE_LOCAL_OLLAMA) ./run.sh
 

README.md

@@ -182,6 +182,14 @@ The models and weights of MiniCPM are completely free for academic research. aft
 
 Enabled by default. Please do use the `strategy=minicpm_v` CLI and URL parameters to use it.
 
+| ⚠️ **Remember to pull the model in Ollama first**       |
+|---------------------------------------------------------|
+| You need to pull the model in Ollama - use the command: |
+| `python client/cli.py llm_pull --model minicpm-v`       |
+| Or, if you have Ollama locally: `ollama pull minicpm-v` |
+
+
+
 ### `llama_vision` 
 
 LLama 3.2 Vision Strategy is licensed on [Meta Community License Agreement](https://ollama.com/library/llama3.2-vision/blobs/0b4284c1f870). Works great for many languages, although due to the number of parameters (90b) this model is probably **the slowest** one.