💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Python agentsaiai-agentsembeddingsinformation-retrievallanguage-modellarge-language-modelsllmnlppythonragretrieval-augmented-generationsearchsearch-enginesemantic-searchsentence-embeddingstransformerstxtaivector-databasevector-search
Update model paths
davidmezzetti4aa9db69fc2d
diff --git a/examples/53_Integrate_LLM_Frameworks.ipynb b/examples/53_Integrate_LLM_Frameworks.ipynbindex 7840d73c..18f9beba 100644--- a/examples/53_Integrate_LLM_Frameworks.ipynb+++ b/examples/53_Integrate_LLM_Frameworks.ipynb@@ -90,7 +90,7 @@"embeddings.index(data)\n","\n","# Create LLM with llama.cpp - GGUF file is automatically downloaded\n",- "llm = LLM(\"TheBloke/Mistral-7B-OpenOrca-GGUF/mistral-7b-openorca.Q4_K_M.gguf\", verbose=True)\n",+ "llm = LLM(\"unsloth/Qwen3-4B-Instruct-2507-GGUF/Qwen3-4B-Instruct-2507-Q4_K_M.gguf\", verbose=True)\n","\n","template = \"\"\"<|im_start|>system\n","You are a friendly assistant. You answer questions from users.<|im_end|>\n",diff --git a/examples/62_RAG_with_llama_cpp_and_external_API_services.ipynb b/examples/62_RAG_with_llama_cpp_and_external_API_services.ipynbindex 7c40270e..62c9dbe2 100644--- a/examples/62_RAG_with_llama_cpp_and_external_API_services.ipynb+++ b/examples/62_RAG_with_llama_cpp_and_external_API_services.ipynb@@ -180,7 +180,7 @@"from txtai import LLM\n","\n","# LLM instance\n",- "llm = LLM(path=\"TheBloke/Mistral-7B-OpenOrca-GGUF/mistral-7b-openorca.Q4_K_M.gguf\")\n",+ "llm = LLM(path=\"unsloth/Qwen3-4B-Instruct-2507-GGUF/Qwen3-4B-Instruct-2507-Q4_K_M.gguf\")\n","\n","# Question and context\n","question = \"Write a list of invented electric-powered devices\"\n",@@ -235,11 +235,11 @@"\n","# Download models\n","!wget https://huggingface.co/second-state/All-MiniLM-L6-v2-Embedding-GGUF/resolve/main/all-MiniLM-L6-v2-Q4_K_M.gguf\n",- "!wget https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF/resolve/main/mistral-7b-openorca.Q4_K_M.gguf\n",+ "!wget https://huggingface.co/unsloth/Qwen3-4B-Instruct-2507-GGUF/blob/main/Qwen3-4B-Instruct-2507-Q4_K_M.gguf\n","\n","# Start local API services\n","!nohup python -m llama_cpp.server --n_gpu_layers -1 --model all-MiniLM-L6-v2-Q4_K_M.gguf --host 127.0.0.1 --port 8000 &> vector.log &\n",- "!nohup python -m llama_cpp.server --n_gpu_layers -1 --model mistral-7b-openorca.Q4_K_M.gguf --chat_format chatml --host 127.0.0.1 --port 8001 &> llm.log &\n",+ "!nohup python -m llama_cpp.server --n_gpu_layers -1 --model Qwen3-4B-Instruct-2507-Q4_K_M.gguf --chat_format chatml --host 127.0.0.1 --port 8001 &> llm.log &\n","!sleep 30"]},