> ## Documentation Index
> Fetch the complete documentation index at: https://docs.moorcheh.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Voyage AI Integration

> Use Voyage embedding models with Moorcheh vector namespaces for semantic search and RAG.

## Voyage AI + Moorcheh

This integration uses the **[Voyage AI](https://www.voyageai.com/)** Python client to generate embeddings and **Moorcheh vector namespaces** to store and search them with ITS ranking.

The example below uses **`voyage-4`** (default **1024** dimensions; other sizes and models are described in the [Voyage embeddings docs](https://docs.voyageai.com/docs/embeddings)).

## Architecture

<CardGroup cols={2}>
  <Card title="Embedding generation" icon="brain">
    `voyageai.Client.embed()` with `input_type="document"` or `"query"` for retrieval
  </Card>

  <Card title="Vector storage" icon="database">
    Store vectors in Moorcheh vector namespaces
  </Card>

  <Card title="Semantic retrieval" icon="magnifying-glass">
    Same model and dimension settings for indexed chunks and queries
  </Card>

  <Card title="Authentication" icon="key">
    `VOYAGE_API_KEY` - see [API key setup](https://docs.voyageai.com/docs/api-key-and-installation)
  </Card>
</CardGroup>

## Prerequisites

* `MOORCHEH_API_KEY` from the [Moorcheh Console](https://console.moorcheh.ai/)
* `VOYAGE_API_KEY` from [Voyage AI](https://www.voyageai.com/)
* Python 3.9+

```bash theme={null}
pip install voyageai moorcheh-sdk python-dotenv
```

The PyPI package is **`voyageai`**. If you see `ModuleNotFoundError: No module named 'voyageai'`, run the install line above with the same Python you use to run your script.

### `.env` file

```bash theme={null}
MOORCHEH_API_KEY=your_moorcheh_key
VOYAGE_API_KEY=your_voyage_key
```

## Model and dimensions

This example uses **`voyage-4`** with the default **1024**-dimensional float embeddings. Set Moorcheh `vector_dimension` to match. You can switch to another [supported model](https://docs.voyageai.com/docs/embeddings#model-choices) (for example `voyage-4-lite`, `voyage-3.5`) and optional `output_dimension` - keep index and query settings aligned.

For retrieval, pass **`input_type="document"`** when embedding stored chunks and **`input_type="query"`** when embedding the search query.

## End-to-end example

```python theme={null}
import os
import textwrap
from typing import List

import voyageai
from dotenv import load_dotenv
from moorcheh_sdk import MoorchehClient

load_dotenv()

MOORCHEH_API_KEY = os.getenv("MOORCHEH_API_KEY", "").strip()
VOYAGE_API_KEY = os.getenv("VOYAGE_API_KEY", "").strip()
if not MOORCHEH_API_KEY or not VOYAGE_API_KEY:
    raise SystemExit("Set MOORCHEH_API_KEY and VOYAGE_API_KEY.")

MODEL = "voyage-4"
VECTOR_DIMENSION = 1024
NAMESPACE = "voyage-embed-demo"
CHUNK_SIZE = 900
CHUNK_OVERLAP = 180


def to_float_vector(values: List[float]) -> List[float]:
    return [float(x) for x in values]


def chunk_text(text: str, chunk_size: int = CHUNK_SIZE, overlap: int = CHUNK_OVERLAP) -> List[str]:
    chunks: List[str] = []
    start = 0
    while start < len(text):
        end = min(start + chunk_size, len(text))
        chunks.append(text[start:end].strip())
        if end == len(text):
            break
        start = max(end - overlap, 0)
    return [c for c in chunks if c]


def extract_text(result: dict) -> str:
    if result.get("text"):
        return str(result["text"])
    metadata = result.get("metadata") or {}
    if isinstance(metadata, dict):
        return str(metadata.get("text") or metadata.get("raw_text") or metadata.get("content") or "")
    return ""


def clean_text(text: str) -> str:
    return " ".join(str(text).split())


def print_result(idx: int, result: dict) -> None:
    metadata = result.get("metadata") or {}
    text_value = clean_text(extract_text(result))
    wrapped = textwrap.fill(text_value, width=100)
    print(f"[{idx}] id={result.get('id')}")
    print(f"score={result.get('score')} label={result.get('label')}")
    print(f"section={metadata.get('section')} source_doc_id={metadata.get('source_doc_id')}")
    print("text:")
    print(wrapped if wrapped else "(no text returned)")
    print("-" * 120)


vo = voyageai.Client(api_key=VOYAGE_API_KEY)
mc = MoorchehClient(api_key=MOORCHEH_API_KEY)

try:
    mc.namespaces.create(
        namespace_name=NAMESPACE,
        type="vector",
        vector_dimension=VECTOR_DIMENSION,
    )
except Exception:
    pass

source_documents = [
    {
        "id": "guide-vector-namespaces",
        "section": "vector-namespace-best-practices",
        "text": (
            "Moorcheh vector namespaces support bring-your-own-embedding workflows. "
            "Use Voyage with input_type document for chunks and query for search strings; match vector_dimension to the embedding size."
        ),
    },
    {
        "id": "guide-search-tuning",
        "section": "semantic-search-tuning",
        "text": (
            "Tune similarity_search top_k and threshold for your use case."
        ),
    },
]

documents = []
for doc in source_documents:
    parts = chunk_text(doc["text"])
    for idx, chunk in enumerate(parts):
        documents.append(
            {
                "id": f"{doc['id']}-chunk-{idx}",
                "text": chunk,
                "source_doc_id": doc["id"],
                "section": doc["section"],
                "chunk_index": idx,
                "total_chunks": len(parts),
            }
        )

texts = [d["text"] for d in documents]
doc_result = vo.embed(texts, model=MODEL, input_type="document")

mc.vectors.upload(
    namespace_name=NAMESPACE,
    vectors=[
        {
            "id": documents[i]["id"],
            "vector": to_float_vector(doc_result.embeddings[i]),
            "text": documents[i]["text"],
            "source": "voyage",
            "model": MODEL,
            "section": documents[i]["section"],
            "source_doc_id": documents[i]["source_doc_id"],
            "chunk_index": documents[i]["chunk_index"],
            "total_chunks": documents[i]["total_chunks"],
        }
        for i in range(len(documents))
    ],
)

query = "How do I use Voyage input_type with Moorcheh?"
q_result = vo.embed([query], model=MODEL, input_type="query")
query_vec = to_float_vector(q_result.embeddings[0])

results = mc.similarity_search.query(
    namespaces=[NAMESPACE],
    query=query_vec,
    top_k=5,
    kiosk_mode=True,
    threshold=0.15,
)

print(f"namespace={NAMESPACE} total_results={len(results.get('results', []))}")
print("=" * 120)
for idx, r in enumerate(results.get("results", []), start=1):
    print_result(idx, r)
```

## Runnable demo script

See `integrations/voyage/voyage_moorcheh_demo.py`.

## Important notes

<AccordionGroup>
  <Accordion title="Vector dimension must match">
    Default for **`voyage-4`** at default settings is **1024**. If you change `output_dimension` or model, recreate or align the namespace dimension.
  </Accordion>

  <Accordion title="Document vs query">
    For retrieval, use **`input_type="document"`** for indexed text and **`input_type="query"`** for the query string.
  </Accordion>

  <Accordion title="Store text on each vector">
    Include `text` on each uploaded vector so search results can return the original chunk.
  </Accordion>
</AccordionGroup>

## Related docs

* [Voyage: Text embeddings](https://docs.voyageai.com/docs/embeddings)
* [Voyage: API key and installation](https://docs.voyageai.com/docs/api-key-and-installation)
* [Create Namespace](/api-reference/namespaces/create)
* [Upload Vector Data](/api-reference/data/upload-vector)
* [Mistral integration](/integrations/mistral/overview)