docs: fix hf embeddings install (#24577)

This commit is contained in:
Erick Friis 2024-07-23 14:03:30 -07:00 committed by GitHub
parent 2d6b0bf3e3
commit 03881c6743
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -8,87 +8,68 @@
"# Sentence Transformers on Hugging Face\n",
"\n",
">[Hugging Face sentence-transformers](https://huggingface.co/sentence-transformers) is a Python framework for state-of-the-art sentence, text and image embeddings.\n",
">One of the embedding models is used in the `HuggingFaceEmbeddings` class.\n",
">We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
"\n",
"`sentence_transformers` package models are originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
">You can use these embedding models from the `HuggingFaceEmbeddings` class."
]
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "06c9f47d",
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchain-huggingface"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "ff9be586",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.1.1\u001b[0m\n",
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
"[-0.0383385568857193, 0.12346469610929489, -0.028642987832427025, 0.05365273728966713, 0.00884537026...\n"
]
}
],
"source": [
"%pip install --upgrade --quiet sentence_transformers > /dev/null"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "861521a9",
"metadata": {},
"outputs": [],
"source": [
"from langchain_huggingface import HuggingFaceEmbeddings"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ff9be586",
"metadata": {},
"outputs": [],
"source": [
"from langchain_huggingface import HuggingFaceEmbeddings\n",
"\n",
"embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
"# Equivalent to SentenceTransformerEmbeddings(model_name=\"all-MiniLM-L6-v2\")"
"\n",
"text = \"This is a test document.\"\n",
"query_result = embeddings.embed_query(text)\n",
"\n",
"# show only the first 100 characters of the stringified vector\n",
"print(str(query_result)[:100] + \"...\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d0a98ae9",
"metadata": {},
"outputs": [],
"source": [
"text = \"This is a test document.\""
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "5d6c682b",
"metadata": {},
"outputs": [],
"source": [
"query_result = embeddings.embed_query(text)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 9,
"id": "bb5e74c0",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[-0.038338493555784225, 0.12346471846103668, -0.028642840683460236, 0.05365276336669922, 0.00884535...\n"
]
}
],
"source": [
"doc_result = embeddings.embed_documents([text, \"This is not a test document.\"])"
"doc_result = embeddings.embed_documents([text, \"This is not a test document.\"])\n",
"print(str(doc_result)[:100] + \"...\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "aaad49f8",
"id": "d18544f5",
"metadata": {},
"outputs": [],
"source": []
@ -110,7 +91,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
"version": "3.11.4"
},
"vscode": {
"interpreter": {