Mistral Embedder

Code

1import asyncio
2
3from kern.knowledge.embedder.mistral import MistralEmbedder
4from kern.knowledge.knowledge import Knowledge
5from kern.vectordb.pgvector import PgVector
6
7embeddings = MistralEmbedder().get_embedding(
8    "The quick brown fox jumps over the lazy dog."
9)
10
11# Print the embeddings and their dimensions
12print(f"Embeddings: {embeddings[:5]}")
13print(f"Dimensions: {len(embeddings)}")
14
15# Example usage:
16knowledge = Knowledge(
17    vector_db=PgVector(
18        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
19        table_name="mistral_embeddings",
20        embedder=MistralEmbedder(),
21    ),
22    max_results=2,
23)
24
25asyncio.run(
26    knowledge.ainsert(
27        path="cookbook/08_knowledge/testing_resources/cv_1.pdf",
28    )
29)

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Set your API key

1export MISTRAL_API_KEY=xxx

Install dependencies

1uv pip install -U sqlalchemy psycopg pgvector mistralai kern-ai

Run PgVector

1docker run -d \
2  -e POSTGRES_DB=ai \
3  -e POSTGRES_USER=ai \
4  -e POSTGRES_PASSWORD=ai \
5  -e PGDATA=/var/lib/postgresql/data/pgdata \
6  -v pgvolume:/var/lib/postgresql/data \
7  -p 5532:5432 \
8  --name pgvector \
9  agnohq/pgvector:16

Run Agent

1python cookbook/08_knowledge/embedders/mistral_embedder.py

1python cookbook/08_knowledge/embedders/mistral_embedder.py