由于业务需求部署的配置 deepseek:32b,linux配置GPU L20 4卡 ,SSD 200g，暂未发现有什么问题，持续观察中
##通用写法，忽略就行，与deepseek无关
import pandas as pd
from openai.embeddings_utils import get_embedding, cosine_similarity
import openai
import os
import logging as logger
from flask_cors import CORS
import os
openai.api_key = os.getenv('OPENAI_API_KEY')class Chatbot():def parse_paper(self, pdf):logger.info("Parsing paper")number_of_pages = len(pdf.pages)logger.info(f"Total number of pages: {number_of_pages}")paper_text = []for i in range(number_of_pages):page = pdf.pages[i]page_text = []def visitor_body(text, cm, tm, fontDict, fontSize):x = tm[4]y = tm[5]# ignore header/footerif (y > 50 and y < 720) and (len(text.strip()) > 1):page_text.append({'fontsize': fontSize,'text': text.strip().replace('\x03', ''),'x': x,'y': y})_ = page.extract_text(visitor_text=visitor_body)blob_font_size = Noneblob_text = ''processed_text = []for t in page_text:if t['fontsize'] == blob_font_size:blob_text += f" {t['text']}"if len(blob_text) >= 2000:processed_text.append({'fontsize': blob_font_size,'text': blob_text,'page': i})blob_font_size = Noneblob_text = ''else:if blob_font_size is not None and len(blob_text) >= 1:processed_text.append({'fontsize': blob_font_size,'text': blob_text,'page': i})blob_font_size = t['fontsize']blob_text = t['text']paper_text += processed_textlogger.info("Done parsing paper")return paper_text1.安装ollama模型运行框架
deepseek-r1:32b
github地址:https://github.com/ollama/ollama
Linux下执行： curl -fsSL https://ollama.com/install.sh | sh
2.ollama相关命令
ollama 服务相关命令
sudo systemctl stop ollama
sudo systemctl status ollama
sudo systemctl start ollama
sudo systemctl restart ollama1.拉取模型
ollama pull xxx模型2.运行模型
ollama run xxx模型
退出聊天cmd /bye3.移除模型
ollama rm xxx模型4.显示模型信息
ollama show xxx模型5.列出计算机上的模型
ollama list6.列出当前加载的模型
ollama ps7.停止当前正在运行的模型
ollama stop xxx模型=====================
linux相关配置地址：https://github.com/ollama/ollama/blob/main/docs/linux.mdollama服务默认端口 11434,修改ollama配置使其可以监听0.0.0.0和修改端口，可以外网访问
1.修改文件
vim /etc/systemd/system/ollama.service2.增加
[Service]
Environment=“OLLAMA_HOST=0.0.0.0:xxxx”3.重现加载
sudo systemctl daemon-reload
sudo systemctl restart ollama
sudo systemctl status ollama4.查看日志
journalctl -u ollama.service5.执行 ollama 命令需要带上 OLLAMA_HOST=127.0.0.1:xxxx
例如 OLLAMA_HOST=127.0.0.1:xxxx ollama psollama相关模型
| Model | Parameters | Size | Download |
|---|---|---|---|
| DeepSeek-R1 | 7B | 4.7GB | ollama run deepseek-r1 |
| DeepSeek-R1 | 671B | 404GB | ollama run deepseek-r1:671b |
| Llama 3.3 | 70B | 43GB | ollama run llama3.3 |
| Llama 3.2 | 3B | 2.0GB | ollama run llama3.2 |
| Llama 3.2 | 1B | 1.3GB | ollama run llama3.2:1b |
| Llama 3.2 Vision | 11B | 7.9GB | ollama run llama3.2-vision |
| Llama 3.2 Vision | 90B | 55GB | ollama run llama3.2-vision:90b |
| Llama 3.1 | 8B | 4.7GB | ollama run llama3.1 |
| Llama 3.1 | 405B | 231GB | ollama run llama3.1:405b |
| Phi 4 | 14B | 9.1GB | ollama run phi4 |
| Phi 3 Mini | 3.8B | 2.3GB | ollama run phi3 |
| Gemma 2 | 2B | 1.6GB | ollama run gemma2:2b |
| Gemma 2 | 9B | 5.5GB | ollama run gemma2 |
| Gemma 2 | 27B | 16GB | ollama run gemma2:27b |
| Mistral | 7B | 4.1GB | ollama run mistral |
| Moondream 2 | 1.4B | 829MB | ollama run moondream |
| Neural Chat | 7B | 4.1GB | ollama run neural-chat |
| Starling | 7B | 4.1GB | ollama run starling-lm |
| Code Llama | 7B | 3.8GB | ollama run codellama |
| Llama 2 Uncensored | 7B | 3.8GB | ollama run llama2-uncensored |
| LLaVA | 7B | 4.5GB | ollama run llava |
| Solar | 10.7B | 6.1GB | ollama run solar |
3.ollama服务提供的api
官方文档地址：https://github.com/ollama/ollama/blob/main/docs/api.md1.与模型聊天api,默认流式，如果不要流式 配置"stream": falsecurl http://localhost:11434/api/chat -d '{"model": "deepseek-r1:32b","messages": [{ "role": "user", "content": "为什么天空是蓝色的？" }],"stream": false
}'
