FrameworkLlamaIndex with DEVUP AI
Build RAG pipelines and agents with LlamaIndex on DEVUP AI models. Use OpenAILike for chat and tool calling, and OpenAILikeEmbedding for embeddings.
System Architecture
How LlamaIndex Connects to DEVUP AI
1. Client
LlamaIndex
Your Python app
2. Gateway
DEVUP OpenAI-compatible API
/v1/chat/completions and /v1/embeddings
3. Inference
Models
DeepSeek-V4-Pro and BAAI/bge-m3
4. Response
Response
Answers, tool calls and vectors
Configuration
Quick Setup
bash
pip install llama-index-core llama-index-llms-openai-like llama-index-embeddings-openai-likepython
import os
from llama_index.core.llms import ChatMessage
from llama_index.llms.openai_like import OpenAILike
llm = OpenAILike(
model="deepseek-ai/DeepSeek-V4-Pro",
api_base="https://api.devupai.com/v1",
api_key=os.environ["DEVUP_API_KEY"],
is_chat_model=True,
is_function_calling_model=True,
context_window=1048576,
max_tokens=512,
timeout=120,
)
response = llm.chat([ChatMessage(role="user", content="Reply with exactly: Salam DEVUP")])
print(response.message.content)RAG
Query Your Documents
python
from llama_index.embeddings.openai_like import OpenAILikeEmbedding
embed_model = OpenAILikeEmbedding(
model_name="BAAI/bge-m3",
api_base="https://api.devupai.com/v1",
api_key=os.environ["DEVUP_API_KEY"],
)
vector = embed_model.get_text_embedding("Salam DEVUP")
print(len(vector))python
from llama_index.core import Document, Settings, VectorStoreIndex
Settings.llm = llm
Settings.embed_model = embed_model
documents = [
Document(text="The internal project codename is Atlas."),
Document(text="The team meets every Tuesday morning."),
Document(text="The office coffee machine is on the second floor."),
]
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine(similarity_top_k=2)
print(query_engine.query("What is the internal project codename?"))Capabilities
Supported Capabilities
Chat and streaming
OpenAILike sends chat requests to DEVUP AI and streams replies as they are generated.
Tool calling
With is_function_calling_model=True, chat_with_tools returns tool calls your code can execute.
Embeddings and RAG
OpenAILikeEmbedding with BAAI/bge-m3 returns 1024-dimensional vectors for VectorStoreIndex.
Local DZD billing
Metered billing in Algerian Dinar with BaridiMob, Edahabia, and CIB local payment support.
