test

app.py

@@ -0,0 +1,13 @@
+import gradio as gr
+import llama_cpp
+
+llm = llama_cpp.Llama.from_pretrained(repo_id="KimChen/bge-m3-GGUF", filename="bge-m3-q4_k_m.gguf", embedding=True)
+
+embeddings = llm.create_embedding("Hello, world!")
+
+def greet(name):
+    embeddings = llm.create_embedding(name)
+    return "Hello " + name + "!!"
+
+demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+demo.launch(mcp_server=True)

requirements.txt

@@ -0,0 +1,5 @@
+whoosh-reloaded==2.7.5
+jieba==0.42.1
+huggingface-hub
+--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+llama-cpp-python