windows默认是CPU运行 需要修改 系统环境变量，添加一个：OLLAMA_GPU_LAYER 值设置为cuda
还是“系统环境变量 添加CUDA_VISIBLE_DEVICES 设置GPU的ID值 （UUID）可以通过nvidia-smi -L来查看显卡的UUID值。
还是“系统环境变量修改OLLAMA服务配置 添加下面两个环境变量：
CUDA_VISIBLE_DEVICES设置值 0,1使用显卡（GPU）0和1
OLLAMA_SCHED_SPREAD设置值1启用负载均衡
This code is for INMP441 to record the sound and save the sound in wav format
I’m using single LEFT channel MONO for my I2S microphone. Make adjustment for your implementation.
PIN CONFIGURATION:
SCK -> 4
WS -> 5
SD -> 18
LR -> 3 (You may also directly Ground the LR pin)
from machine import Pin
from machine import I2S
#======= USER CONFIGURATION =======
RECORD_TIME_IN_SECONDS = 3
SAMPLE_RATE_IN_HZ = 16000
filename = 'mic.wav'
#======= USER CONFIGURATION =======
WAV_SAMPLE_SIZE_IN_BITS = 16
WAV_SAMPLE_SIZE_IN_BYTES = WAV_SAMPLE_SIZE_IN_BITS // 8
MIC_SAMPLE_BUFFER_SIZE_IN_BYTES = 4096
SDCARD_SAMPLE_BUFFER_SIZE_IN_BYTES = MIC_SAMPLE_BUFFER_SIZE_IN_BYTES // 2 # why divide by 2? only using 16-bits of 32-bit samples
NUM_SAMPLE_BYTES_TO_WRITE = int(RECORD_TIME_IN_SECONDS * SAMPLE_RATE_IN_HZ * WAV_SAMPLE_SIZE_IN_BYTES)
NUM_SAMPLES_IN_DMA_BUFFER = 256
NUM_CHANNELS = 1
#====== FUNCTIONS =========
def snip_16_mono(samples_in, samples_out):
num_samples = len(samples_in) // 4
for i in range(num_samples):
samples_out[2*i] = samples_in[4*i + 2]
samples_out[2*i + 1] = samples_in[4*i + 3]
return num_samples * 2
def create_wav_header(sampleRate, bitsPerSample, num_channels, num_samples):
datasize = int(num_samples * num_channels * bitsPerSample // 8)
o = bytes("RIFF",'ascii') # (4byte) Marks file as RIFF
o += (datasize + 36).to_bytes(4,'little') # (4byte) File size in bytes excluding this and RIFF marker
o += bytes("WAVE",'ascii') # (4byte) File type
o += bytes("fmt ",'ascii') # (4byte) Format Chunk Marker
o += (16).to_bytes(4,'little') # (4byte) Length of above format data
o += (1).to_bytes(2,'little') # (2byte) Format type (1 - PCM)
o += (num_channels).to_bytes(2,'little') # (2byte)
o += (sampleRate).to_bytes(4,'little') # (4byte)
o += (sampleRate * num_channels * bitsPerSample // 8).to_bytes(4,'little') # (4byte)
o += (num_channels * bitsPerSample // 8).to_bytes(2,'little') # (2byte)
o += (bitsPerSample).to_bytes(2,'little') # (2byte)
o += bytes("data",'ascii') # (4byte) Data Chunk Marker
o += (datasize).to_bytes(4,'little') # (4byte) Data size in bytes
return o
################## MAIN #########################
#FOR ICS43434 only
PIN_I2S_LR = 3
Pin(PIN_I2S_LR, Pin.OUT, value=0)
###############
audio_in = I2S(1,
sck=Pin(4), ws=Pin(5), sd=Pin(18),
mode=I2S.RX,
bits=32,
format=I2S.MONO,
rate=SAMPLE_RATE_IN_HZ,
ibuf=20000,
)
wav = open(filename,'wb')
# create header for WAV file and write to SD card
wav_header = create_wav_header(
SAMPLE_RATE_IN_HZ,
WAV_SAMPLE_SIZE_IN_BITS,
NUM_CHANNELS,
SAMPLE_RATE_IN_HZ * RECORD_TIME_IN_SECONDS
)
num_bytes_written = wav.write(wav_header)
# allocate sample arrays
# memoryview used to reduce heap allocation in while loop
mic_samples = bytearray(MIC_SAMPLE_BUFFER_SIZE_IN_BYTES)
mic_samples_mv = memoryview(mic_samples)
wav_samples = bytearray(SDCARD_SAMPLE_BUFFER_SIZE_IN_BYTES)
wav_samples_mv = memoryview(wav_samples)
num_sample_bytes_written_to_wav = 0
print('Starting')
# read 32-bit samples from I2S microphone, snip upper 16-bits, write snipped samples to WAV file
while num_sample_bytes_written_to_wav < NUM_SAMPLE_BYTES_TO_WRITE:
# try to read a block of samples from the I2S microphone
# readinto() method returns 0 if no DMA buffer is full
num_bytes_read_from_mic = audio_in.readinto(mic_samples_mv)
if num_bytes_read_from_mic > 0:
# snip upper 16-bits from each 32-bit microphone sample
num_bytes_snipped = snip_16_mono(mic_samples_mv[:num_bytes_read_from_mic], wav_samples_mv)
num_bytes_to_write = min(num_bytes_snipped, NUM_SAMPLE_BYTES_TO_WRITE - num_sample_bytes_written_to_wav)
num_bytes_written = wav.write(wav_samples_mv[:num_bytes_to_write])
num_sample_bytes_written_to_wav += num_bytes_written
wav.close()
audio_in.deinit()
print('Done')
print(f'{num_sample_bytes_written_to_wav} sample bytes written to WAV file')环境部署
pip install torch transformers docling_core -i https://mirrors.aliyun.com/pypi/simple/pip install transformers numpy huggingface_hub -i https://mirrors.aliyun.com/pypi/simple/
export HF_ENDPOINT=https://hf-mirror.com
huggingface-cli download ds4sd/SmolDocling-256M-preview --local-dir SmolDoclin-256M
# Prerequisites:
# pip install torch
# pip install docling_core
# pip install transformers
import torch
from docling_core.types.doc import DoclingDocument
from docling_core.types.doc.document import DocTagsDocument
from transformers import AutoProcessor, AutoModelForVision2Seq
from transformers.image_utils import load_image
from pathlib import Path
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
# Load images
image = load_image("https://upload.wikimedia.org/wikipedia/commons/7/76/GazettedeFrance.jpg")
# Initialize processor and model
processor = AutoProcessor.from_pretrained("ds4sd/SmolDocling-256M-preview")
model = AutoModelForVision2Seq.from_pretrained(
"ds4sd/SmolDocling-256M-preview",
torch_dtype=torch.bfloat16,
_attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager",
).to(DEVICE)
# Create input messages
messages = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "Convert this page to docling."}
]
},
]
# Prepare inputs
prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
inputs = processor(text=prompt, images=[image], return_tensors="pt")
inputs = inputs.to(DEVICE)
# Generate outputs
generated_ids = model.generate(**inputs, max_new_tokens=8192)
prompt_length = inputs.input_ids.shape[1]
trimmed_generated_ids = generated_ids[:, prompt_length:]
doctags = processor.batch_decode(
trimmed_generated_ids,
skip_special_tokens=False,
)[0].lstrip()
# Populate document
doctags_doc = DocTagsDocument.from_doctags_and_image_pairs([doctags], [image])
print(doctags)
# create a docling document
doc = DoclingDocument(name="Document")
doc.load_from_doctags(doctags_doc)
# export as any format
# HTML
# Path("Out/").mkdir(parents=True, exist_ok=True)
# output_path_html = Path("Out/") / "example.html"
# doc.save_as_html(output_path_html)
# MD
print(doc.export_to_markdown())
1.Docker 与 Docker-compose安装
sudo apt update && sudo apt install docker.io apparmor -y
sudo curl -L "https://github.com/docker/compose/releases/download/v2.20.3/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
sudo chmod +x /usr/local/bin/docker-compose
测试：docker-compose
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/docker
docker-compose -f docker-compose.yml up -d
直接通过命令 docker ps 查看信息；
浏览器访问 http://IP 即可进入
angthingllm 可以本地桌面和搭建服务器web端。
下面是WEB端的搭建（需要DOCKER）：
Ubuntu下Docker sudo apt update && sudo apt install docker.io apparmor -y
anythingLLM 的Docker部署命令：
export STORAGE_LOCATION=$HOME/anythingllm && \
mkdir -p $STORAGE_LOCATION && \
touch "$STORAGE_LOCATION/.env" && \
docker run -d -p 3001:3001 \
--cap-add SYS_ADMIN \
-v ${STORAGE_LOCATION}:/app/server/storage \
-v ${STORAGE_LOCATION}/.env:/app/server/.env \
-e STORAGE_DIR="/app/server/storage" \
mintplexlabs/anythingllm访问你的http://IP:3001 即可
E5 V2 CPU 不支持 会在首页设置模型处报错，docker直接下线。
vultr 新建4C 8G 可以运行
需要给anythingllm目录整体给予777 权限 即可,下面步骤:
chmod -R 777 anythingllm docker logs报错/usr/local/bin/docker-entrypoint.sh: line 7: 105 Illegal instruction (core dumped) node /app/server/index.js
在网页设置中 无法进入下一步，网页显示报错
Failed to save LLM settings: Failed to fetch
在默认设置的目录需要写入权限 直接777 完事 chmod -R 777 $HOME/anythingllm