dftmsg

app.py

@@ -1,72 +1,18 @@
-import streamlit as st
-from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
-from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from llama_index.llms.huggingface import HuggingFaceLLM
+from openai import OpenAI
 
-st.set_page_config(page_title="llama_index_demo", page_icon="🦜🔗")
-st.title("llama_index_demo")
+base_url = "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
+api_key = "eyJ0eXBlIjoiSldUIiwiYWxnIjoiSFM1MTIifQ.eyJqdGkiOiIxMTIwNDk3OSIsInJvbCI6IlJPTEVfUkVHSVNURVIiLCJpc3MiOiJPcGVuWExhYiIsImlhdCI6MTczMzQxMjU1NCwiY2xpZW50SWQiOiJlYm1ydm9kNnlvMG5semFlazF5cCIsInBob25lIjoiMTUxMzcxMTY1MzEiLCJ1dWlkIjoiYmVlYTk0NTQtNWE5OS00OGNkLTgxNzctZDdjZWYzNmQwNTAxIiwiZW1haWwiOiIiLCJleHAiOjE3NDg5NjQ1NTR9.0-DNSkviINNJhGmx49-kUfTSRvyXNrT4LXU1sB01FprErwGCVinJStN5aNsaHjF2K95Pl7B15SQ_fa2l8cIT3Q"
+model="internlm2.5-latest"
 
-# 初始化模型
-@st.cache_resource
-def init_models():
-    embed_model = HuggingFaceEmbedding(
-        model_name="/root/model/sentence-transformer"
-    )
-    Settings.embed_model = embed_model
+client = OpenAI(
+    api_key=api_key , 
+    base_url=base_url,
+)
 
-    llm = HuggingFaceLLM(
-        model_name="/root/model/internlm2-chat-1_8b",
-        tokenizer_name="/root/model/internlm2-chat-1_8b",
-        model_kwargs={"trust_remote_code": True},
-        tokenizer_kwargs={"trust_remote_code": True}
-    )
-    Settings.llm = llm
+chat_rsp = client.chat.completions.create(
+    model=model,
+    messages=[{"role": "user", "content": "xtuner是什么？"}],
+)
 
-    documents = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()
-    index = VectorStoreIndex.from_documents(documents)
-    query_engine = index.as_query_engine()
-
-    return query_engine
-
-# 检查是否需要初始化模型
-if 'query_engine' not in st.session_state:
-    st.session_state['query_engine'] = init_models()
-
-def greet2(question):
-    response = st.session_state['query_engine'].query(question)
-    return response
-
-
-# Store LLM generated responses
-if "messages" not in st.session_state.keys():
-    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]
-
-    # Display or clear chat messages
-for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.write(message["content"])
-
-def clear_chat_history():
-    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]
-
-st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
-
-# Function for generating LLaMA2 response
-def generate_llama_index_response(prompt_input):
-    return greet2(prompt_input)
-
-# User-provided prompt
-if prompt := st.chat_input():
-    st.session_state.messages.append({"role": "user", "content": prompt})
-    with st.chat_message("user"):
-        st.write(prompt)
-
-# Gegenerate_llama_index_response last message is not from assistant
-if st.session_state.messages[-1]["role"] != "assistant":
-    with st.chat_message("assistant"):
-        with st.spinner("Thinking..."):
-            response = generate_llama_index_response(prompt)
-            placeholder = st.empty()
-            placeholder.markdown(response)
-    message = {"role": "assistant", "content": response}
-    st.session_state.messages.append(message)
+for choice in chat_rsp.choices:
+    print(choice.message.content)

b.py

@@ -0,0 +1,22 @@
+from openai import OpenAI
+
+base_url = "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
+api_key = "sk-请填写准确的 token！"
+model="internlm2.5-latest"
+
+# base_url = "https://api.siliconflow.cn/v1"
+# api_key = "sk-请填写准确的 token！"
+# model="internlm/internlm2_5-7b-chat"
+
+client = OpenAI(
+    api_key=api_key , 
+    base_url=base_url,
+)
+
+chat_rsp = client.chat.completions.create(
+    model=model,
+    messages=[{"role": "user", "content": "xtuner是什么？"}],
+)
+
+for choice in chat_rsp.choices:
+    print(choice.message.content)

requirements.txt

@@ -1,11 +1,5 @@
-einops==0.7.0
-protobuf==5.26.1
-llama-index==0.10.38
-llama-index-llms-huggingface==0.2.0
-transformers[torch]==4.41.1
-huggingface_hub[inference]==0.23.1
-huggingface_hub==0.23.1
-sentence-transformers==2.7.0
-sentencepiece==0.2.0
-llama-index-embeddings-huggingface==0.2.0
-llama-index-embeddings-instructor==0.1.3
+llama-index==0.11.20
+llama-index-llms-replicate==0.3.0
+llama-index-llms-openai-like==0.2.0
+llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-instructor==0.2.1