Pakistan's First Oracle Blog
Blog By Fahd Mirza ChughtaiFahd Mirzahttp://www.blogger.com/profile/14722451950835849728noreply@blogger.comBlogger627125
Updated: 3 hours 35 min ago
Easiest RAG Tutorial for Beginners on Free Google Colab
This video is a step-by-step tutorial to learn RAG in an easy way with LlamaIndex on your own data in free google colab.
Code:
!pip install llama-index faiss-cpu pandas python-dotenv openai transformers numpy
!pip install llama-index-agent-openai llama-index-cli llama-index-core llama-index-embeddings-openai
!pip install llama-index-llms-openai llama-index-program-openai llama-index-question-gen-openai llama-index-readers-file
!pip install llama-index-readers-llama-parse llama-index-vector-stores-faiss llama-parse llama-index-indices-managed-llama-cloud
from llama_index.core.readers import SimpleDirectoryReader
from llama_index.core import Settings
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.readers.file import PagedCSVReader
from llama_index.vector_stores.faiss import FaissVectorStore
from llama_index.core.ingestion import IngestionPipeline
from llama_index.core import VectorStoreIndex
import faiss
import os
import pandas as pd
from google.colab import userdata
os.environ['OPENAI_API_KEY']=userdata.get('OPENAI_API_KEY')
EMBED_DIMENSION=512
Settings.llm = OpenAI(model="gpt-3.5-turbo")
Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small", dimensions=EMBED_DIMENSION)
file_path = ('/content/minifinance.csv')
data = pd.read_csv(file_path)
data.head()
fais_index = faiss.IndexFlatL2(EMBED_DIMENSION)
vector_store = FaissVectorStore(faiss_index=fais_index)
csv_reader = PagedCSVReader()
reader = SimpleDirectoryReader(
input_files=[file_path],
file_extractor= {".csv": csv_reader}
)
docs = reader.load_data()
print(docs[0].text)
pipeline = IngestionPipeline(
vector_store=vector_store,
documents=docs
)
nodes = pipeline.run()
vector_store_index = VectorStoreIndex(nodes)
query_engine = vector_store_index.as_query_engine(similarity_top_k=2)
response = query_engine.query("which products are sold in Canada?")
response.response
Categories: DBA Blogs
Live Face Swapping in Call with AI - Easy Installation on Windows for Free - Rope Pearl Live
This video shows how to locally install Rope Pearl Live on Windows for for live swapping using Webcam and for live streaming the swapped videos using virtual camera.
Code:
Clone the repository to your folder by downloading the zip file:
https://github.com/argenspin/Rope-Live.git
cd Rope-Live
conda create -n Rope python=3.10.13
conda activate Rope
conda install cuda-runtime=11.8.0 cudnn=8.9.2.26 gputil=1.4.0 -c pytorch -c nvidia -c conda-forge
python -m pip install -r requirements.txt
Download the required models
To get access to all the features of Rope, you need to download the models from here. You need all of the files.
Place the downloaded model files in the Rope-Live/models folder
Set up OBS Virtual Camera
Start OBS.
Click "Start Virtual Camera" (bottom right), then "Stop Virtual Camera".
Close OBS.
Start the application by running Rope.bat file
Categories: DBA Blogs
How To Fine-Tune AI Model with Online Direct Preference Optimization Locally on Own Dataset
This video is a step-by-step tutorial to use Online DPO to fine-tune a model locally on custom dataset. ODPO is a new alignment method from DeepMind to boost the performance of LLMs.
Code:
conda create -n dpo python=3.11 -y && conda activate dpo
pip install torch
pip install datasets dataclasses
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
git clone https://github.com/huggingface/trl.git && cd trl
git checkout d57e4b726561e5ae58fdc335f34029052944a4a3
pip install -e .
conda install jupyter -y
pip uninstall charset_normalizer -y
pip install charset_normalizer
jupyter notebook
from datasets import Dataset
from trl import OnlineDPOConfig, OnlineDPOTrainer
from transformers import (
AutoModelForCausalLM,
AutoModelForSequenceClassification,
AutoTokenizer,
)
NUM_DUMMY_SAMPLES = 100
tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM-135M-Instruct")
tokenizer.add_special_tokens({"pad_token": "[PAD]"})
# The model to optimise
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM-135M-Instruct")
# The reference model to calculate the KL divergence against
ref_model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM-135M-Instruct")
# The model to score completions with. In practice, you will need a reward model.
reward_model = AutoModelForSequenceClassification.from_pretrained("HuggingFaceTB/SmolLM-135M-Instruct", num_labels=1)
train_dataset = Dataset.from_dict(
{"prompt": ["Q: Hi how are you? A:"] * NUM_DUMMY_SAMPLES})
eval_dataset = Dataset.from_dict(
{"prompt": ["Q: What do you like to eat A:"] * NUM_DUMMY_SAMPLES})
args = OnlineDPOConfig(output_dir="online-dpo-model")
trainer = OnlineDPOTrainer(
model=model,
ref_model=ref_model,
reward_model=reward_model,
args=args,
tokenizer=tokenizer,
train_dataset=train_dataset,
eval_dataset=eval_dataset,
)
trainer.train()
Categories: DBA Blogs
Install MiniG Locally - Long Context Model for Novel and Story Writing with Images
This video shows how to locally install MiniG model which is trained on a synthesis dataset of over 120 million entries and has 1M token context window. It deals with both text and images.
Code:
conda create -n lm python=3.11 -y && conda activate lm
pip install torch
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
pip install --upgrade sentencepiece
conda install jupyter -y
pip uninstall charset_normalizer -y
pip install charset_normalizer
jupyter notebook
pip install tiktoken torchvision
import torch
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
)
device = "cuda"
tokenizer = AutoTokenizer.from_pretrained("CausalLM/miniG",trust_remote_code=True)
query = "What is Happiness?"
inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}],
add_generation_prompt=True,
tokenize=True,
return_tensors="pt",
return_dict=True
)
inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
"CausalLM/miniG",
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
trust_remote_code=True
).to(device).eval()
gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
outputs = model.generate(**inputs, **gen_kwargs)
outputs = outputs[:, inputs['input_ids'].shape[1]:]
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
#===================
#For Images:
#==================
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
tokenizer = AutoTokenizer.from_pretrained("CausalLM/miniG", trust_remote_code=True)
query = 'Which lane should I drive in this image?'
image = Image.open("/home/Ubuntu/images/lane.png").convert('RGB')
inputs = tokenizer.apply_chat_template([{"role": "user", "image": image, "content": query}],
add_generation_prompt=True, tokenize=True, return_tensors="pt",
return_dict=True) # chat mode
inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
"CausalLM/miniG",
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
trust_remote_code=True
).to(device).eval()
gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
outputs = model.generate(**inputs, **gen_kwargs)
outputs = outputs[:, inputs['input_ids'].shape[1]:]
print(tokenizer.decode(outputs[0]))
Categories: DBA Blogs
Install RAG Me Up with Ollama Locally - Free RAG with Any Dataset
This video shows how to install and use RAG Me Up which is a generic framework (server + UIs) that enables you do to RAG on your own dataset.
Code:
conda create -n rag python=3.11 -y && conda activate rag
sudo apt update
sudo apt install openjdk-17-jre
sudo apt install openjdk-17-jdk
java --version
Install Scala : To install Scala, it is recommended to use cs setup, the Scala installer powered by Coursier. It installs everything necessary to use the latest Scala release from a command line
curl -fL https://github.com/coursier/coursier/releases/latest/download/cs-x86_64-pc-linux.gz | gzip -d > cs && chmod +x cs && ./cs setup
source ~/.profileInstall SBT, simple build tool for scala :
cs setup
sbt --script-version
This should install the latest stable version of sbt
git clone https://github.com/UnderstandLingBV/RAGMeUp.git cd RAGMeUp/server
pip install -r requirements.txt
python3 server.py
For Scala UI:
Run sbt run from the server/scala
Categories: DBA Blogs
Rope Pearl Installation - Easy Tutorial for Deepfake Face Swap - Free and Private Face Fusion
This video shows how to locally install Rope Pearl on Windows for one click face swap in any video free and private. You can fuse multiple faces in deepfake easily.
Code:
1- Install Choco
Open Powershell as Administrator and run following:
Set-ExecutionPolicy Bypass -Scope Process -Force;
[System.Net.ServicePointManager]::SecurityProtocol
= [System.Net.ServicePointManager]::SecurityProtocol -bor 3072; iex
((New-Object System.Net.WebClient).DownloadString
('https://chocolatey.org/install.ps1'))
2- Install following pre-reqs
choco install python --version=3.10.0
choco install git
choco install ffmpeg
3- Install Visual Studio from
https://visualstudio.microsoft.com/visual-cpp-build-tools/
4- git clone https://github.com/Hillobar/Rope
5- cd Rope
6- create the virtual environment
python -m venv venv
7- activate the local venv
.\venv\Scripts\activate
8- check if you have installed the correct python version (Python 3.10.X)
python --version
9- install the dependencies for Rope
.\venv\Scripts\pip.exe install -r .\requirements.txt
10- copy all the files from this page under Assets ,
https://github.com/Hillobar/Rope/releases/tag/Sapphire
and save them in Rope\Models folder
11- Run .\Rope.bat
Categories: DBA Blogs
Top Free High-Quality AI Datasets Sites
This video shows where to find quality and free datasets for LLMs easily.
ARCS Data Sets
https://csr.lanl.gov/data/
Microsoft Datasets
https://www.microsoft.com/en-us/research/tools/?facet%5Bdate%5D%5Bfixed%5D=any&facet%5Btax%5D%5Bmsr-product-type%5D[]=243083&filter_queries%5B%5D=open&pg=1&sort_by=most-relevant
AWS Open Datasets
https://registry.opendata.aws/
Google Datasets
https://datasetsearch.research.google.com/
PEW Research
https://www.pewresearch.org/search/dataset
Azure Open Datasets
https://azure.microsoft.com/en-us/products/open-datasets
Categories: DBA Blogs
Easy Tutorial to Build Full Free RAG Pipeline from Scratch with Your Own Data
This video shows how to install Haystack with Ollama locally for free end-to-end RAG pipeline with your own documents.
Code:
conda create -n hay python=3.11 -y && conda activate hay
pip install torch
pip install haystack-ai==2.2.4
pip install haystack-experimental==0.1.0
pip install sentence-transformers==3.0.1
pip install transformers==4.42.3
pip install ollama-haystack
conda install jupyter -y
pip uninstall charset_normalizer -y
pip install charset_normalizer
jupyter notebook
import transformers
import torch
from haystack_integrations.components.generators.ollama import OllamaGenerator
generator = OllamaGenerator(model="llama3.1",
url = "http://localhost:11434/api/generate",
generation_kwargs={
"num_predict": 100,
"temperature": 0.9,
})
print(generator.run("Who is the best American actor?"))
========
from haystack_integrations.components.generators.ollama import OllamaGenerator
from haystack import Pipeline, Document
from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
from haystack.components.builders.prompt_builder import PromptBuilder
from haystack.document_stores.in_memory import InMemoryDocumentStore
template = """
Given the following information, answer the question.
Context:
{% for document in documents %}
{{ document.content }}
{% endfor %}
Question: {{ query }}?
"""
docstore = InMemoryDocumentStore()
docstore.write_documents([Document(content="I really like summer"),
Document(content="My favorite sport is soccer"),
Document(content="I don't like reading sci-fi books"),
Document(content="I don't like crowded places"),])
generator = OllamaGenerator(model="llama3.1",
url = "http://localhost:11434/api/generate",
generation_kwargs={
"num_predict": 100,
"temperature": 0.9,
})
pipe = Pipeline()
pipe.add_component("retriever", InMemoryBM25Retriever(document_store=docstore))
pipe.add_component("prompt_builder", PromptBuilder(template=template))
pipe.add_component("llm", generator)
pipe.connect("retriever", "prompt_builder.documents")
pipe.connect("prompt_builder", "llm")
result = pipe.run({"prompt_builder": {"query": query},"retriever": {"query": query}})
print(result)
Categories: DBA Blogs
Roop - One-Click Face Swap in Video with AI - Step by Step Tutorial
This video shows how to locally install Roop which enables you to take a video and replace the face in it with a face of your choice. You only need one image of the desired face. No dataset, no training. This is an alternate of Deep Live Cam tool for AI Face Swap.
Code:
conda create -n roop python=3.11 -y && conda activate roop
git clone https://github.com/s0md3v/roop.git && cd roop
pip install -r requirements.txt
python3 run.py --execution-provider cuda
Categories: DBA Blogs
Install MinerU Locally to Create LLM Dataset from PDF Files
This video shows how to install MinerU which is a LLM-powered tool that converts PDFs into machine-readable formats (e.g., markdown, JSON), allowing for easy extraction into any format to create datasets.
Code:
git clone https://github.com/opendatalab/MinerU.git && cd MinerU
conda create -n MinerU python=3.10 && conda activate MinerU
pip install magic-pdf[full]==0.7.0b1 --extra-index-url https://wheels.myhloli.com
magic-pdf --version
git lfs install
mkdir model
cd model
git lfs clone https://huggingface.co/wanderkid/PDF-Extract-Kit
change magic-pdf.json for models-dir and cuda
wget https://github.com/opendatalab/MinerU/raw/master/demo/small_ocr.pdf
magic-pdf -p small_ocr.pdf
Categories: DBA Blogs
Adobe Magic Fixup - Edit Images with Simple Cut and Paste - Install Locally
This video shows how to install Magic Fixup Locally. It enables users to edit images with simple a cut-and-paste like approach, and fixup those edits automatically.
Code:
git clone https://github.com/adobe-research/MagicFixup.git && cd MagicFixup
conda env create -f environment.yaml -v
conda activate MagicFixup
wget https://drive.google.com/file/d/1zOcDcJzCijbGr9I9adC0Cv6yzW60U9TQ/view?usp=share_link
python3 magicfu_gradio.py --checkpoint magic_fu_open_source_full_model.pt
Categories: DBA Blogs
Install Phi 3.5 Vision Locally for OCR and Image Chat
This video shows how to locally install Phi-3.5-vision which is a lightweight, state-of-the-art open multimodal model with a focus on very high-quality, reasoning dense data both on text and vision.
Code:
pip install torch
pip install --upgrade transformers
pip install accelerate huggingface_hub
pip install numpy Pillow Requests torchvision
jupyter notebook
from IPython.display import Markdown, display
from PIL import Image
import requests
from transformers import AutoModelForCausalLM
from transformers import AutoProcessor
model_id = "microsoft/Phi-3.5-vision-instruct"
# Note: set _attn_implementation='eager' if you don't have flash_attn installed
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map="cuda",
trust_remote_code=True,
torch_dtype="auto",
_attn_implementation='flash_attention_2'
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
# Load the local image
image = Image.open("/home/Ubuntu/images/1.png")
# Prepare the input
messages = [
{"role": "user", "content": "<|image_1|> Describe this image.",}
]
prompt = processor.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
inputs = processor(prompt, [image], return_tensors="pt").to("cuda:0")
# Generate the response
generation_args = {
"max_new_tokens": 1000,
"temperature": 0.0,
"do_sample": False,
}
generate_ids = model.generate(**inputs,
eos_token_id=processor.tokenizer.eos_token_id,
**generation_args)
# Remove input tokens
generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
response = processor.batch_decode(generate_ids,
skip_special_tokens=True,
clean_up_tokenization_spaces=False)[0]
print(response)
Categories: DBA Blogs
CogVideoX-2B - Install Locally to Create Videos from Text
This video shows how to locally install CogVideoX-2B which is an open-source video generation model.
Code:
conda create -n cog python=3.11 -y && conda activate cog
git clone https://github.com/THUDM/CogVideo.git && CogVideo
pip install -r requirements.txt
pip install --upgrade opencv-python transformers diffusers
conda install jupyter -y
pip uninstall charset_normalizer -y
pip install charset_normalizer
jupyter notebook
import torch
from diffusers import CogVideoXPipeline
from diffusers.utils import export_to_video
prompt = "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene."
pipe = CogVideoXPipeline.from_pretrained(
"THUDM/CogVideoX-2b",
torch_dtype=torch.float16
)
pipe.enable_model_cpu_offload()
prompt_embeds, _ = pipe.encode_prompt(
prompt=prompt,
do_classifier_free_guidance=True,
num_videos_per_prompt=1,
max_sequence_length=226,
device="cuda",
dtype=torch.float16,
)
video = pipe(
num_inference_steps=50,
guidance_scale=6,
prompt_embeds=prompt_embeds,
).frames[0]
export_to_video(video, "output.mp4", fps=8)
Categories: DBA Blogs
Free LLM Dataset Creation with Ollama Locally - Easy Tutorial
This video is a step-by-step tutorial to create your own custom dataset from your database schema locally with free model from Ollama.
Code:
import json
import ollama
def make_llama_3_prompt(user, system="", assistant=""):
system_prompt = ""
if system:
system_prompt = (
f"<|start_header_id|>system<|end_header_id|>\n\n{system}<|eot_id|>"
)
user_prompt = f"<|start_header_id|>user<|end_header_id|>\n\n{user}<|eot_id|>"
assistant_prompt = f"<|start_header_id|>assistant<|end_header_id|>\n\n{assistant}<|eot_id|>" if assistant else "<|start_header_id|>assistant<|end_header_id|>\n\n"
return f"<|begin_of_text|>{system_prompt}{user_prompt}{assistant_prompt}"
def get_movie_schema():
return """\
0|Title|TEXT eg. "Inception"
1|Director|TEXT eg. "Christopher Nolan"
2|Year|INT eg. "2010"
3|Rating|TEXT eg. "PG-13"
4|Runtime|TEXT eg. "148 min" castable to int
5|Genre|TEXT eg. "Sci-Fi"
6|Box_Office|TEXT eg. "$829,895,144" and when null has a value "N/A"
"""
def generate_question_and_query():
system = "You are a data analyst with 10 years of experience writing complex SQL queries.\n"
system += (
"Consider a table called 'movies' with the following schema (columns)\n"
)
system += get_movie_schema()
system += "Consider the following questions, and queries used to answer them:\n"
question = """What is the highest-grossing movie of all time?"""
sql = "SELECT Title, Box_Office FROM movies WHERE Box_Office != 'N/A' ORDER BY CAST(REPLACE(Box_Office, ',', '') AS INTEGER) DESC LIMIT 1;"
system += "Question: " + question + "\n"
system += "Query: " + sql + "\n"
user = "Write a question and a query that are similar but different to those above.\n"
user += "Format the question and query as a JSON object, i.e.\n"
user += '{"question" : str, "sql_query": str }.\n'
user += "Make sure to only return me valid sqlite SQL query generated as response to the question. Don't give me any comments. Just return question and query as JSON objects. Make sure query is relevant to the question. Make sure each query is complete and ends with a ;\n"
prompt = make_llama_3_prompt(user, system)
# Generate the result from the model
result = ollama.generate(model='llama3.1', prompt=prompt)
# Inspect and parse the result['response']
response_str = result['response']
try:
response_dict = json.loads(response_str)
except json.JSONDecodeError as e:
print("Failed to parse response as JSON:", e)
response_dict = {}
return response_dict
def save_to_jsonl(data, file_path):
with open(file_path, 'a') as f:
for entry in data:
f.write(json.dumps(entry) + '\n')
def main():
output_file_path = 'questions_queries.jsonl'
num_iterations = 10 # Define how many questions and queries you want to generate
all_questions_queries = []
for _ in range(num_iterations):
question_and_query = generate_question_and_query()
all_questions_queries.append(question_and_query)
save_to_jsonl(all_questions_queries, output_file_path)
print(f"Saved {num_iterations} questions and queries to {output_file_path}")
# Execute the main function
if __name__ == "__main__":
main()
Categories: DBA Blogs
How to Install Flux AI Models Locally for Image Generation Easily
This video shows how to install Flux.1-Dev and Flux.1-Schnell model locally in comfyUI and how to generate midjourney like images.
Code:
conda create -n comfy python=3.11 -y && conda activate comfy
git clone https://github.com/comfyanonymous/ComfyUI.git && cd ComfyUI
pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu121
pip install -r requirements.txt
python3 main.py
http://localhost:8188
cd ComfyUI/models/clip AND COPY clip_l.safetensors & t5xxl_fp16.safetensors FROM https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main
cd ComfyUI/models/vae/ AND COPY ae.safetensors FROM https://huggingface.co/black-forest-labs/FLUX.1-dev
cd ComfyUI/models/unet/ AND COPY flux1-dev.safetensors FROM https://huggingface.co/black-forest-labs/FLUX.1-dev
cd ComfyUI/models/loras/ AND COPY flux_realism_lora.safetensors
FROM https://huggingface.co/comfyanonymous/flux_RealismLora_converted_comfyui/tree/main
Go To https://comfyanonymous.github.io/ComfyUI_examples/flux/
Categories: DBA Blogs
Deep Live Cam Local Installation Easy Guide for Face Swap and Deepfake Video on Webcam
This is step-by-step easy tutorial to install Deep Live Cam for real time face swap and one-click video deepfake with only a single image (uncensored) locally on Windows.
Code:
1- Install Choco
Open Powershell as Administrator and run following:
Set-ExecutionPolicy Bypass -Scope Process -Force; [System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor 3072; iex ((New-Object System.Net.WebClient).DownloadString('https://chocolatey.org/install.ps1'))
2- Install following pre-reqs
choco install python --version=3.10.0
choco install git
choco install ffmepg
3- Install Visual Studio from https://visualstudio.microsoft.com/visual-cpp-build-tools/
3- git clone https://github.com/hacksider/Deep-Live-Cam.git and cd Deep-Live-Cam
4- Download 2 models from https://huggingface.co/hacksider/deep-live-cam/tree/main and put it in Deep-Live-Cam\models folder
5- cd Deep-Live-Cam and pip install -r requirements.txt
6- If on CPU, run python run.py
For GPU:
7- Install CUDA Toolkit 11.8 from https://developer.nvidia.com/cuda-11-8-0-download-archive
8- Install dependencies:
pip uninstall onnxruntime onnxruntime-gpu
pip install onnxruntime-gpu==1.16.3
9- python run.py --execution-provider cuda
Enjoy
Categories: DBA Blogs
Mem0 with Ollama Locally - Memory Layer for Personalized AI
This video is a step-by-step easy tutorial to install Mem0 locally and integrate it with Ollama local model.
Code:
conda create -n mem python=3.11 -y && conda activate mem
pip install torch
pip install -U transformers sentencepiece accelerate
pip install sentence_transformers
pip install ollama
pip install mem0ai
import os
from mem0 import Memory
os.environ["OPENAI_API_KEY"] = ""
config = {
"llm": {
"provider": "ollama",
"config": {
"model": "llama3.1:latest",
"temperature": 0.1,
"max_tokens": 2000,
}
}
}
m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})
# Get all memories
all_memories = m.get_all()
print(all_memories)
# Get a single memory by ID
specific_memory = m.get("59565340-c742-4e09-8128-702e810cb4fd")
print(specific_memory)
related_memories = m.search(query="alice hobbies?", user_id="alice")
print(related_memories)
result = m.update(memory_id="59565340-c742-4e09-8128-702e810cb4fd", data="Visited Brisbane in Winter")
print(result)
m.delete(memory_id="59565340-c742-4e09-8128-702e810cb4fd") # Delete a memory
m.delete_all(user_id="alice") # Delete all memories
all_memories = m.get_all()
print(all_memories)
Categories: DBA Blogs
Workflows in LlamaIndex - Tutorial to Build Complex AI Applications with Events
This video shows how to install and use LlamaIndex Workflows which is a mechanism for orchestrating actions in the increasingly complex AI application.
Code:
conda create -n workflow python=3.11 -y && conda activate workflow
pip install llama-index
pip install llama-index-llms-openai
conda install jupyter -y
pip uninstall charset_normalizer -y
pip install charset_normalizer
jupyter notebook
from llama_index.core.workflow import (
Event,
StartEvent,
StopEvent,
Workflow,
step,
)
from llama_index.llms.openai import OpenAI
class WeatherEvent(Event):
location: str
forecast: str | None
class WeatherFlow(Workflow):
llm = OpenAI()
@step()
async def get_location(self, ev: StartEvent) -> WeatherEvent:
location = "Sydney"
forecast = "" # or some default value
return WeatherEvent(location=location, forecast=forecast)
@step()
async def get_forecast(self, ev: WeatherEvent) -> WeatherEvent:
location = ev.location
prompt = f"Get the current weather forecast for {location}."
response = await self.llm.acomplete(prompt)
return WeatherEvent(location=location, forecast=str(response))
@step()
async def format_forecast(self, ev: WeatherEvent) -> StopEvent:
location = ev.location
forecast = ev.forecast
formatted_forecast = f"Weather in {location}: {forecast}"
return StopEvent(result=formatted_forecast)
w = WeatherFlow(timeout=60, verbose=False)
result = await w.run()
print(str(result))
Categories: DBA Blogs
Install Perplexica with SearXNG and Ollama and Llama 3.1 for Local AI Search Engine for Free
This video shows how to locally install Perplexica with SearXNG and Ollama Llama 3.1 model and do AI-powered search.
Code:
conda create -n px python=3.11 -y && conda activate px
pip install torch transformers accelerate huggingface_hub sentencepiece
SearXNG:
git clone https://github.com/searxng/searxng && cd searxng
under searx directory in settings.yml file, change following:
search:
formats:
- html
- json
sudo chmod 666 /var/run/docker.sock
make docker.build
docker run --rm -d -p 32768:8080 -v "${PWD}/searxng:/etc/searxng" -e "BASE_URL=http://localhost:$PORT/" -e "INSTANCE_NAME=my-instance" searxng/searxng
http://localhost:32768
Ollama:
curl -fsSL https://ollama.com/install.sh | sh
ollama pull llama3
ollama pull bgesmall
perplexica :
git clone https://github.com/ItzCrazyKns/Perplexica.git && cd Perplexica
cp sample.config.toml config.toml
vi config.toml change following:
[API_ENDPOINTS]
SEARXNG = "http://localhost:32768"
OLLAMA = "http://localhost:11434"
sudo chmod 666 /var/run/docker.sock
docker compose up -d
http://localhost:3000
Categories: DBA Blogs
Get Llama 3.1 70B-Level AI Quality from 8B with Ollama Locally for Free
This video is a step-by-step easy tutorial to get quality of Llama 3.1 70B from Llama 3.1 8B with Ollama locally. It's inspired by Matt Shumer GPT Prompt Engineer.
Code:
import os
import re
import json
import sys
from ollama import Client
client = Client(host='http://localhost:11434')
# Define model names
small_model = "llama3.1"
big_model = "llama3.1:70b"
def generate_candidate_prompts(task, prompt_example, response_example):
system_prompt = """Given an example training sample, create seven additional samples for the same task that are even better.
Each example should contain:
1. Ensure the new examples are diverse and unique from one another.
2. They should all be perfect. If you make a mistake, this system won't work.
Respond in this format:
PUT_PROMPT_HERE
PUT_RESPONSE_HERE
PUT_PROMPT_HERE
PUT_RESPONSE_HERE
...
"""
user_content = f"""{task}
{prompt_example}
{response_example}
"""
response = client.chat(
model=big_model,
messages=[
{"role": "system", "content": system_prompt},
{"role": "user", "content": user_content}
],
options={
"max_tokens": 4000,
"temperature": 0.5
}
)
response_text = response['message']['content']
# Parse out the prompts and responses
prompts_and_responses = []
# Split examples by the delimiter
examples = response_text.split('PUT_PROMPT_HERE')[1:]
for example in examples:
parts = example.split('PUT_RESPONSE_HERE')
if len(parts) == 2:
prompt, response = parts
prompts_and_responses.append({'prompt': prompt.strip(), 'response': response.strip()})
return prompts_and_responses
def generate_system_prompt(task, prompt_examples):
system_prompt = """Given a user-description of their task and a set of prompt / response pairs (it'll be in JSON for easy reading)
for the types of outputs we want to generate given inputs, write a fantastic system prompt that describes
the task to be done perfectly.
1. Do this perfectly.
2. Respond only with the system prompt, and nothing else. No other text will be allowed.
Respond in this format:
WRITE_SYSTEM_PROMPT_HERE
"""
user_content = f"""{task}
{json.dumps(prompt_examples, indent=2)}
"""
response = client.chat(
model=big_model,
messages=[
{"role": "system", "content": system_prompt},
{"role": "user", "content": user_content}
],
options={
"max_tokens": 4000,
"temperature": 0.5
}
)
response_text = response['message']['content']
# Directly use the response text since the prompt specifies it should be the only content
generated_system_prompt = response_text.strip()
return generated_system_prompt
def test_small_model(generated_examples, prompt_example, system_prompt):
messages = [{"role": "system", "content": system_prompt}]
for example in generated_examples:
messages.append({"role": "user", "content": example['prompt']})
messages.append({"role": "assistant", "content": example['response']})
messages.append({"role": "user", "content": prompt_example.strip()})
response = client.chat(
model=small_model,
messages=messages,
options={
"max_tokens": 2000,
"temperature": 0.5
}
)
response_text = response['message']['content']
return response_text
def run_conversion_process(task, prompt_example, response_example):
print('Generating the prompts / responses...')
# Generate candidate prompts
generated_examples = generate_candidate_prompts(task, prompt_example, response_example)
print('Prompts / responses generated. Now generating system prompt...')
# Generate the system prompt
system_prompt = generate_system_prompt(task, generated_examples)
print('System prompt generated:', system_prompt)
print(f'\n\nTesting the new prompt on {small_model}, using your input example...')
# Test the generated examples and system prompt with the small model
small_model_response = test_small_model(generated_examples, prompt_example, system_prompt)
print(f'{small_model} responded with:')
print(small_model_response)
print('\n\n!! CHECK THE FILE DIRECTORY, THE PROMPT IS NOW SAVED THERE !!')
# Create a dictionary with all the relevant information
result = {
"task": task,
"initial_prompt_example": prompt_example,
"initial_response_example": response_example,
"generated_examples": generated_examples,
"system_prompt": system_prompt,
"small_model_response": small_model_response
}
# Save the small model prompt to a Python file
with open("small_model_prompt.py", "w") as file:
file.write('system_prompt = """' + system_prompt + '"""\n\n')
file.write('messages = [\n')
for example in generated_examples:
file.write(' {"role": "user", "content": """' + example['prompt'] + '"""},\n')
file.write(' {"role": "assistant", "content": """' + example['response'] + '"""},\n')
file.write(' {"role": "user", "content": """' + prompt_example.strip() + '"""}\n')
file.write(']\n')
return result
task = "refactoring code"
prompt_example = """def hello():
total = 0
total = total + 1
return total"""
response_example = """def hello():
total = 1
return total
"""
result = run_conversion_process(task, prompt_example, response_example)
print(result)
Categories: DBA Blogs