依赖冲突太麻烦了

.ipynb_checkpoints/download_hf-checkpoint.py

@@ -0,0 +1,7 @@
+import os
+
+# 设置环境变量
+os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
+
+# 下载模型
+os.system('huggingface-cli download --resume-download sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 --local-dir /root/model/sentence-transformer')

.ipynb_checkpoints/llamaindex_RAG-checkpoint.py

@@ -0,0 +1,48 @@
+import os 
+os.environ['NLTK_DATA'] = '/root/nltk_data'
+
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
+from llama_index.core.settings import Settings
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.legacy.callbacks import CallbackManager
+from llama_index.llms.openai_like import OpenAILike
+
+
+# Create an instance of CallbackManager
+callback_manager = CallbackManager()
+
+api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
+model = "internlm2.5-latest"
+api_key = os.getenv("API_KEY")
+
+# api_base_url =  "https://api.siliconflow.cn/v1"
+# model = "internlm/internlm2_5-7b-chat"
+# api_key = "请填写 API Key"
+
+
+
+llm =OpenAILike(model=model, api_base=api_base_url, api_key=api_key, is_chat_model=True,callback_manager=callback_manager)
+
+
+#初始化一个HuggingFaceEmbedding对象，用于将文本转换为向量表示
+embed_model = HuggingFaceEmbedding(
+#指定了一个预训练的sentence-transformer模型的路径
+    model_name="/root/model/sentence-transformer"
+)
+#将创建的嵌入模型赋值给全局设置的embed_model属性，
+#这样在后续的索引构建过程中就会使用这个模型。
+Settings.embed_model = embed_model
+
+#初始化llm
+Settings.llm = llm
+
+#从指定目录读取所有文档，并加载数据到内存中
+documents = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()
+#创建一个VectorStoreIndex，并使用之前加载的文档来构建索引。
+# 此索引将文档转换为向量，并存储这些向量以便于快速检索。
+index = VectorStoreIndex.from_documents(documents)
+# 创建一个查询引擎，这个引擎可以接收查询并返回相关文档的响应。
+query_engine = index.as_query_engine()
+response = query_engine.query("Qwen2Attention是什么?")
+
+print(response)

.ipynb_checkpoints/requirements-checkpoint.txt

@@ -1,119 +1,6 @@
-aiohappyeyeballs==2.4.3
-aiohttp==3.11.7
-aiosignal==1.3.1
-altair==5.5.0
-annotated-types==0.7.0
-anyio==4.6.2.post1
-async-timeout==5.0.1
-attrs==24.2.0
-beautifulsoup4==4.12.3
-blinker==1.9.0
-cachetools==5.5.0
-certifi==2024.8.30
-charset-normalizer==3.4.0
-click==8.1.7
-dataclasses-json==0.6.7
-deprecated==1.2.15
-dirtyjson==1.0.8
-distro==1.9.0
-einops==0.7.0
-exceptiongroup==1.2.2
-filelock==3.16.1
-filetype==1.2.0
-frozenlist==1.5.0
-fsspec==2024.10.0
-gitdb==4.0.11
-gitpython==3.1.43
-greenlet==3.1.1
-h11==0.14.0
-httpcore==1.0.7
-httpx==0.27.2
-huggingface-hub==0.26.2
-idna==3.10
-instructorembedding==1.0.1
-jinja2==3.1.4
-jiter==0.7.1
-joblib==1.4.2
-jsonschema==4.23.0
-jsonschema-specifications==2024.10.1
-llama-cloud==0.1.5
 llama-index==0.11.20
-llama-index-agent-openai==0.3.4
-llama-index-cli==0.3.1
-llama-index-core==0.11.23
+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
-llama-index-embeddings-openai==0.2.5
-llama-index-indices-managed-llama-cloud==0.6.0
-llama-index-legacy==0.9.48.post4
-llama-index-llms-openai==0.2.16
-llama-index-llms-openai-like==0.2.0
-llama-index-llms-replicate==0.3.0
-llama-index-multi-modal-llms-openai==0.2.3
-llama-index-program-openai==0.2.0
-llama-index-question-gen-openai==0.2.0
-llama-index-readers-file==0.2.2
-llama-index-readers-llama-parse==0.3.0
-llama-parse==0.5.15
-markdown-it-py==3.0.0
-markupsafe==3.0.2
-marshmallow==3.23.1
-mdurl==0.1.2
-mpmath==1.3.0
-multidict==6.1.0
-mypy-extensions==1.0.0
-narwhals==1.14.2
-nest-asyncio==1.6.0
-networkx==3.4.2
-nltk==3.9.1
-numpy==1.26.4
-openai==1.55.0
-packaging==24.2
-pandas==2.2.3
-pillow==10.4.0
-propcache==0.2.0
-protobuf==5.26.1
-pyarrow==18.0.0
-pydantic==2.10.1
-pydantic-core==2.27.1
-pydeck==0.9.1
-pygments==2.18.0
-pypdf==4.3.1
-python-dateutil==2.9.0.post0
-pytz==2024.2
-pyyaml==6.0.2
-referencing==0.35.1
-regex==2024.11.6
-requests==2.32.3
-rich==13.9.4
-rpds-py==0.21.0
-safetensors==0.4.5
-scikit-learn==1.5.2
-scipy==1.14.1
-sentence-transformers==2.7.0
-six==1.16.0
-smmap==5.0.1
-sniffio==1.3.1
-soupsieve==2.6
-sqlalchemy==2.0.36
-streamlit==1.39.0
-striprtf==0.0.26
-sympy==1.13.1
-tenacity==8.5.0
-threadpoolctl==3.5.0
-tiktoken==0.8.0
-tokenizers==0.13.3
-torch==2.1.2
-torchaudio==2.1.2
-torchvision==0.16.0
-tornado==6.4.2
-tqdm==4.67.1
-transformers==4.46.3
-triton
-typing-extensions==4.12.2
-typing-inspect==0.9.0
-tzdata==2024.2
-urllib3==2.2.3
-watchdog==5.0.3
-wrapt==1.17.0
-yarl==1.18.0
+streamlit==1.39.0

.ipynb_checkpoints/test_internlm-checkpoint.py

@@ -0,0 +1,24 @@
+from openai import OpenAI
+import os
+
+base_url = "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
+# api_key = "sk-请填写准确的 token！"
+api_key = os.getenv("API_KEY")
+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": "Qwen2Attention是什么？"}],
+)
+
+for choice in chat_rsp.choices:
+    print(choice.message.content)

requirements.txt

@@ -0,0 +1,6 @@
+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
+streamlit==1.39.0