Mixedbread Cloud: A Unified API for RAG Pipelines

pip set up mixedbread openai

import os
import time
from mixedbread import Mixedbread
from openai import OpenAI

# --- Configuration ---
# 1. Get your Mixedbread API Key
mxbai_api_key = os.getenv("MXBAI_API_KEY")

# 2. Get your OpenAI API Key
openai_api_key = os.getenv("OPENAI_API_KEY")

# 3. Outline the trail to the FOLDER containing your PDF information
pdf_folder_path = "/work/docs"

# 4. Vector Retailer Configuration
vector_store_name = "Abid Articles"

# 5. OpenAI Mannequin Configuration
openai_model = "gpt-4.1-nano-2025-04-14"

# --- Initialize Shoppers ---
mxbai = Mixedbread(api_key=mxbai_api_key)
openai_client = OpenAI(api_key=openai_api_key)

import glob

pdf_files_to_upload = glob.glob(os.path.be part of(pdf_folder_path, "*.pdf")) # Discover all .pdf information

print(f"Discovered {len(pdf_files_to_upload)} PDF information to add:")
for pdf_path in pdf_files_to_upload:
    print(f"  - {os.path.basename(pdf_path)}")

uploaded_file_ids = []
print("nUploading information...")
for pdf_path in pdf_files_to_upload:
    filename = os.path.basename(pdf_path)
    print(f"  Importing {filename}...")
    with open(pdf_path, "rb") as f:
        upload_response = mxbai.information.create(file=f)
        file_id = upload_response.id
        uploaded_file_ids.append(file_id)
        print(f"    -> Uploaded efficiently. File ID: {file_id}")

print(f"nSuccessfully uploaded {len(uploaded_file_ids)} information.")

Discovered 4 PDF information to add:
  - Constructing Agentic Software utilizing Streamlit and Langchain.pdf
  - Deploying DeepSeek Janus Professional regionally.pdf
  - High-quality-Tuning GPT-4o.pdf
  - The best way to Attain $500k on Upwork.pdf

Importing information...
  Importing Constructing Agentic Software utilizing Streamlit and Langchain.pdf...
    -> Uploaded efficiently. File ID: 8a538aa9-3bde-4498-90db-dbfcf22b29e9
  Importing Deploying DeepSeek Janus Professional regionally.pdf...
    -> Uploaded efficiently. File ID: 52c7dfed-1f9d-492c-9cf8-039cc64834fe
  Importing High-quality-Tuning GPT-4o.pdf...
    -> Uploaded efficiently. File ID: 3eaa584f-918d-4671-9b9c-6c91d5ca0595
  Importing The best way to Attain $500k on Upwork.pdf...
    -> Uploaded efficiently. File ID: 0e47ba93-550a-4d4b-9da1-6880a748402b

Efficiently uploaded 4 information.

vector_store_response = mxbai.vector_stores.create(
    title=vector_store_name,
    file_ids=uploaded_file_ids # Add all uploaded file IDs throughout creation
)
vector_store_id = vector_store_response.id

print("nMonitoring file processing standing (this will take a while)...")
all_files_processed = False
max_wait_time = 600 # Most seconds to attend (10 minutes, regulate as wanted)
check_interval = 20 # Seconds between checks
start_time = time.time()
final_statuses = {}

whereas not all_files_processed and (time.time() - start_time)  0:
     print("nWarning: Some information failed processing. RAG will proceed utilizing solely the efficiently processed information.")
elif not all_files_processed:
     print(f"nWarning: File processing didn't full for all information inside the most wait time ({max_wait_time}s). RAG will proceed utilizing solely the efficiently processed information.")

Monitoring file processing standing (this will take a while)...
  Standing Examine (Elapsed: 0s): Accomplished: 0, Failed: 0, In Progress: 4, Pending: 0, Different: 0 / Complete: 4
  Standing Examine (Elapsed: 21s): Accomplished: 0, Failed: 0, In Progress: 4, Pending: 0, Different: 0 / Complete: 4
  Standing Examine (Elapsed: 42s): Accomplished: 4, Failed: 0, In Progress: 0, Pending: 0, Different: 0 / Complete: 4

--- Processing Abstract ---
Complete information processed: 4
Efficiently accomplished: 4
Failed or Cancelled: 0

user_query = "The best way to Deploy Deepseek Janus Professional?"

retrieved_context = ""

search_results = mxbai.vector_stores.search(
    vector_store_ids=[vector_store_id], # Search inside our newly created retailer
    question=user_query,
    top_k=10 # Retrieve prime 10 related chunks throughout all paperwork
)

if search_results.information:
    # Mix the content material of the chunks right into a single context string
    context_parts = []
    for i, chunk in enumerate(search_results.information):
        context_parts.append(f"Chunk {i+1} from '{chunk.filename}' (Rating: {chunk.rating:.4f}):n{chunk.content material}n---")
    retrieved_context = "n".be part of(context_parts)
else:
    retrieved_context = "No context was retrieved." 

prompt_template = f"""
You're an assistant answering questions based mostly *solely* on the offered context from a number of paperwork.
Don't use any prior data. If the context doesn't include the reply to the query, state that clearly.

Context from the paperwork:
---
{retrieved_context}
---

Query: {user_query}

Reply:
"""

response = openai_client.chat.completions.create(
    mannequin=openai_model,
    messages=[
        {"role": "user", "content": prompt_template}
    ],
    temperature=0.2,
    max_tokens=500
)

final_answer = response.selections[0].message.content material.strip()

print(final_answer)

To deploy DeepSeek Janus Professional regionally, observe these steps:

1. Set up Docker Desktop from https://www.docker.com/ and set it up with default settings. On Home windows, guarantee WSL is put in if prompted.

2. Clone the Janus repository by working:
   ```
   git clone https://github.com/kingabzpro/Janus.git
   ```
3. Navigate into the cloned listing:
   ```
   cd Janus
   ```
4. Construct the Docker picture utilizing the offered Dockerfile:
   ```
   docker construct -t janus .
   ```
5. Run the Docker container with the next command, which units up port forwarding, GPU entry, and protracted storage:
   ```
   docker run -it --rm -p 7860:7860 --gpus all --name janus_pro -e TRANSFORMERS_CACHE=/root/.cache/huggingface -v huggingface:/root/.cache/huggingface janus:newest
   ```
6. Look forward to the container to obtain the mannequin and begin the Gradio software. As soon as working, entry the app at http://localhost:7860/.

7. The appliance has two sections: one for picture understanding and one for picture era, permitting you to add pictures, ask for descriptions or poems, and generate pictures based mostly on prompts.

This course of allows you to deploy DeepSeek Janus Professional regionally in your machine.