llama-index,uncharted and llama2:7b run locally to generate Index

题意：本地运行 llama-index、uncharted 以及 llama2:7b 来生成索引


题目配景：

I wanted to use llama-index locally with ollama and llama3:8b to index utf-8 json file. I dont have a gpu. I use uncharted to convert docs into json. Now If it is not possible to use llama-index locally without GPU I wanted to use hugging face inference API. But I am not certain if it is free. Can anyone suggest a way?
This is my python code:

1. from llama_index.core import Document, SimpleDirectoryReader, VectorStoreIndex
2.     from llama_index.llms.ollama import Ollama
3.     import json
4.     from llama_index.core import Settings
5.    
6.    
7.     # Convert the JSON document into LlamaIndex Document objects
8.     with open('data/UBER_2019.json', 'r',encoding='utf-8') as f:
9.         json_doc = json.load(f)
10.     documents = [Document(text=str(doc)) for doc in json_doc]
11.    
12.     # Initialize Ollama with the local LLM
13.     ollama_llm = Ollama(model="llama3:8b")
14.     Settings.llm = ollama_llm
15.    
16.     # Create the index using the local LLM
17.     index = VectorStoreIndex.from_documents(documents)#, llm=ollama_llm)

复制代码

But i keep getting error that there is no OPENAI key. I wanted to use llama2 so that i dont require OPENAI key
Can anyone suggest what i am doing wrong? Also can i use huggingfaceinference API to do indexing of a local json file for free?

题目办理：

You are not setting the embedding model, so I think Llama Index is defaulting to OpenAI.
You must specify an embedding model that does not require an API key.
You can use Ollama:

1. from llama_index.embeddings.ollama import OllamaEmbedding
3. # Using Nomic
4. Settings.embed_model = OllamaEmbedding(model_name="nomic-embed-text")
6. # Using Llama
7. Settings.embed_model = OllamaEmbedding(model_name="llama2")

复制代码

But there are many options in the documentation like this, this, this

免责声明：如果侵犯了您的权益，请联系站长，我们会及时删除侵权内容，谢谢合作！更多信息从访问主页：qidao123.com:ToB企服之家，中国第一个企服评测及商务社交产业平台。