github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-25 16:13:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: Update jina embedding notebook to include multimodal capability (#22594)

Browse Source 
After merging the [PR #22416 to include Jina AI multimodal
capabilities](https://github.com/langchain-ai/langchain/pull/22416), we
updated the Jina AI embedding notebook accordingly.
This commit is contained in:
Francesco Kruk 2024-06-07 02:02:20 +02:00 committed by GitHub
parent be79ce9336
commit 344adad056
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 101 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

108
docs/docs/integrations/text_embedding/jina.ipynb
View File

@ -10,6 +10,16 @@
"Let's load the Jina Embedding class."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2f0a1567-6273-47a3-b19d-c30af2470810",
"metadata": {},
"outputs": [],
"source": [
"pip install -U langchain-community"
]
},
{
"cell_type": "code",
"execution_count": null,
@ -17,7 +27,11 @@
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.embeddings import JinaEmbeddings"
"import requests\n",
"from langchain_community.embeddings import JinaEmbeddings\n",
"from numpy import dot\n",
"from numpy.linalg import norm\n",
"from PIL import Image"
]
},
{
@ -27,9 +41,11 @@
"metadata": {},
"outputs": [],
"source": [
"embeddings = JinaEmbeddings(\n",
"text_embeddings = JinaEmbeddings(\n",
" jina_api_key=\"jina_*\", model_name=\"jina-embeddings-v2-base-en\"\n",
")"
")\n",
"\n",
"image_embeddings = JinaEmbeddings(jina_api_key=\"jina_*\", model_name=\"jina-clip-v1\")"
]
},
{
@ -39,7 +55,15 @@
"metadata": {},
"outputs": [],
"source": [
"text = \"This is a test document.\""
"text = \"This is a test document.\"\n",
"\n",
"image = \"https://avatars.githubusercontent.com/u/126733545?v=4\"\n",
"\n",
"description = \"Logo of a parrot and a chain on green background\"\n",
"\n",
"im = Image.open(requests.get(image, stream=True).raw)\n",
"print(\"Image:\")\n",
"display(im)"
]
},
{
@ -49,7 +73,7 @@
"metadata": {},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
"query_result = text_embeddings.embed_query(text)"
]
},
{
@ -69,7 +93,7 @@
"metadata": {},
"outputs": [],
"source": [
"doc_result = embeddings.embed_documents([text])"
"doc_result = text_embeddings.embed_documents([text])"
]
},
{
@ -81,6 +105,76 @@
"source": [
"print(doc_result)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ac2aace1-27af-4c4f-96f8-8e8b20d95b98",
"metadata": {},
"outputs": [],
"source": [
"image_result = image_embeddings.embed_images([image])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6687808c-1977-4128-a960-888bb82c46e1",
"metadata": {},
"outputs": [],
"source": [
"print(image_result)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2844ef7c-cf9b-4e28-b627-09887aaa0a6d",
"metadata": {},
"outputs": [],
"source": [
"description_result = image_embeddings.embed_documents([description])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "23372332-2ea3-4e4a-abc8-8307d45ebc95",
"metadata": {},
"outputs": [],
"source": [
"print(description_result)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "08d3ba5e-8957-4b10-97e3-40359ab165a6",
"metadata": {},
"outputs": [],
"source": [
"cosine_similarity = dot(image_result[0], description_result[0]) / (\n",
" norm(image_result[0]) * norm(description_result[0])\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6be56ff9-774b-4347-a5cf-57d8db9e2cf2",
"metadata": {},
"outputs": [],
"source": [
"print(cosine_similarity)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7f280807-a02b-4d4e-8ebd-01be33117999",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -99,7 +193,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
"version": "3.12.2"
}
},
"nbformat": 4,