mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-03 10:12:33 +00:00
Added ipynb documentation
This commit is contained in:
dhirup
parent
fd0e46691f
commit
d23ee15f8d
276
docs/docs/integrations/vectorstores/coherence.ipynb
Normal file
276
docs/docs/integrations/vectorstores/coherence.ipynb
Normal file
@ -0,0 +1,276 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c92e2cb6-d75b-4321-bf73-69b07d244aa7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Coherence\n",
|
||||
"\n",
|
||||
"This notebook covers how to get started with the `Coherence` vector store.\n",
|
||||
"\n",
|
||||
">[Coherence](https://www.oracle.com/java/coherence/) is an in-memory data grid that provides a distributed, fault-tolerant, and scalable platform for managing and accessing data. It is primarily used for high-performance, mission-critical enterprise applications that require low-latency access to large datasets. In addition to the commercially available product, Oracle also offers [Coherence CE (Community Edition)](https://github.com/oracle/coherence)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "77db1e62-622e-46c1-8f1d-4f32a42f22da",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup\n",
|
||||
"\n",
|
||||
"To access `Coherence` vector stores you'll need to install the `langchain-coherence` integration package.\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"pip install langchain_coherence\n",
|
||||
"```\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a266cffc-0407-4fd3-b905-f42b0770125c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Usage\n",
|
||||
"\n",
|
||||
"Before using LangChain's CoherenceVectorStore you must ensure that a Coherence server ([Coherence CE](https://github.com/oracle/coherence) 25.03+ or [Oracle Coherence](https://www.oracle.com/java/coherence/) 14.1.2+) is running \n",
|
||||
"\n",
|
||||
"For local development, we recommend using the Coherence CE container image:\n",
|
||||
"```aiignore\n",
|
||||
"docker run -d -p 1408:1408 ghcr.io/oracle/coherence-ce:25.03.2\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"### Add Documents and retrieve them:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "1e432d99-4750-48b6-a5f9-e8680f9832e9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"from langchain_core.documents import Document\n",
|
||||
"from langchain_core.embeddings import Embeddings\n",
|
||||
"from langchain_huggingface.embeddings import HuggingFaceEmbeddings\n",
|
||||
"\n",
|
||||
"from coherence import NamedMap, Session\n",
|
||||
"from langchain_core.vectorstores.coherence_store import CoherenceVectorStore\n",
|
||||
"\n",
|
||||
"session: Session = await Session.create()\n",
|
||||
"try:\n",
|
||||
" named_map: NamedMap[str, Document] = await session.get_map(\"my-map\")\n",
|
||||
" embedding :Embeddings = HuggingFaceEmbeddings(\n",
|
||||
" model_name=\"sentence-transformers/all-MiniLM-l6-v2\")\n",
|
||||
" # this embedding generates vectors of dimension 384\n",
|
||||
" cvs :CoherenceVectorStore = await CoherenceVectorStore.create(\n",
|
||||
" named_map,embedding,384)\n",
|
||||
" d1 :Document = Document(id=\"1\", page_content=\"apple\")\n",
|
||||
" d2 :Document = Document(id=\"2\", page_content=\"orange\")\n",
|
||||
" documents = [d1, d2]\n",
|
||||
" await cvs.aadd_documents(documents)\n",
|
||||
"\n",
|
||||
" ids = [doc.id for doc in documents]\n",
|
||||
" l = await cvs.aget_by_ids(ids)\n",
|
||||
" assert len(l) == len(ids)\n",
|
||||
" print(\"====\")\n",
|
||||
" for e in l:\n",
|
||||
" print(e)\n",
|
||||
"finally:\n",
|
||||
" await session.close()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "eee71605-8d1f-431d-b796-07274b036da3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Delete Documents:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "97e0d922-7208-46be-bade-71f56ce8c586",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"from langchain_core.documents import Document\n",
|
||||
"from langchain_core.embeddings import Embeddings\n",
|
||||
"from langchain_huggingface.embeddings import HuggingFaceEmbeddings\n",
|
||||
"\n",
|
||||
"from coherence import NamedMap, Session\n",
|
||||
"from langchain_core.vectorstores.coherence_store import CoherenceVectorStore\n",
|
||||
"\n",
|
||||
"session: Session = await Session.create()\n",
|
||||
"try:\n",
|
||||
" named_map: NamedMap[str, Document] = await session.get_map(\"my-map\")\n",
|
||||
" embedding :Embeddings = HuggingFaceEmbeddings(\n",
|
||||
" model_name=\"sentence-transformers/all-MiniLM-l6-v2\")\n",
|
||||
" # this embedding generates vectors of dimension 384\n",
|
||||
" cvs :CoherenceVectorStore = await CoherenceVectorStore.create(\n",
|
||||
" named_map,embedding,384)\n",
|
||||
" d1 :Document = Document(id=\"1\", page_content=\"apple\")\n",
|
||||
" d2 :Document = Document(id=\"2\", page_content=\"orange\")\n",
|
||||
" documents = [d1, d2]\n",
|
||||
" await cvs.aadd_documents(documents)\n",
|
||||
"\n",
|
||||
" ids = [doc.id for doc in documents]\n",
|
||||
" await cvs.adelete(ids)\n",
|
||||
"finally:\n",
|
||||
" await session.close()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a8c6ad91-ee54-486a-888f-cbfc89be75fd",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Similarity Search:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ffe24b05-7bf1-4eaa-a030-6ac3a0446f29",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_core.documents import Document\n",
|
||||
"from langchain_core.embeddings import Embeddings\n",
|
||||
"from langchain_huggingface.embeddings import HuggingFaceEmbeddings\n",
|
||||
"\n",
|
||||
"from coherence import NamedMap, Session\n",
|
||||
"from langchain_core.vectorstores.coherence_store import CoherenceVectorStore\n",
|
||||
"\n",
|
||||
"def test_data():\n",
|
||||
" d1 :Document = Document(id=\"1\", page_content=\"apple\")\n",
|
||||
" d2 :Document = Document(id=\"2\", page_content=\"orange\")\n",
|
||||
" d3 :Document = Document(id=\"3\", page_content=\"tiger\")\n",
|
||||
" d4 :Document = Document(id=\"4\", page_content=\"cat\")\n",
|
||||
" d5 :Document = Document(id=\"5\", page_content=\"dog\")\n",
|
||||
" d6 :Document = Document(id=\"6\", page_content=\"fox\")\n",
|
||||
" d7 :Document = Document(id=\"7\", page_content=\"pear\")\n",
|
||||
" d8 :Document = Document(id=\"8\", page_content=\"banana\")\n",
|
||||
" d9 :Document = Document(id=\"9\", page_content=\"plum\")\n",
|
||||
" d10 :Document = Document(id=\"10\", page_content=\"lion\")\n",
|
||||
"\n",
|
||||
" documents = [d1, d2, d3, d4, d5, d6, d7, d8, d9, d10]\n",
|
||||
" return documents\n",
|
||||
"\n",
|
||||
"async def test_asimilarity_search():\n",
|
||||
" documents = test_data()\n",
|
||||
" session: Session = await Session.create()\n",
|
||||
" try:\n",
|
||||
" named_map: NamedMap[str, Document] = await session.get_map(\"my-map\")\n",
|
||||
" embedding :Embeddings = HuggingFaceEmbeddings(\n",
|
||||
" model_name=\"sentence-transformers/all-MiniLM-l6-v2\")\n",
|
||||
" # this embedding generates vectors of dimension 384\n",
|
||||
" cvs :CoherenceVectorStore = await CoherenceVectorStore.create(\n",
|
||||
" named_map,embedding,384)\n",
|
||||
" await cvs.aadd_documents(documents)\n",
|
||||
" ids = [doc.id for doc in documents]\n",
|
||||
" l = await cvs.aget_by_ids(ids)\n",
|
||||
" assert len(l) == 10\n",
|
||||
"\n",
|
||||
" result = await cvs.asimilarity_search(\"fruit\")\n",
|
||||
" assert len(result) == 4\n",
|
||||
" print(\"====\")\n",
|
||||
" for e in result:\n",
|
||||
" print(e)\n",
|
||||
" finally:\n",
|
||||
" await session.close()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5411477e-5905-4a96-80d8-b8d2238c4bc4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Similarity Search by vector :"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "9713d8bc-db9d-46e7-9fec-2613c2635ad7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"from langchain_core.documents import Document\n",
|
||||
"from langchain_core.embeddings import Embeddings\n",
|
||||
"from langchain_huggingface.embeddings import HuggingFaceEmbeddings\n",
|
||||
"\n",
|
||||
"from coherence import NamedMap, Session\n",
|
||||
"from langchain_core.vectorstores.coherence_store import CoherenceVectorStore\n",
|
||||
"\n",
|
||||
"def test_data():\n",
|
||||
" d1 :Document = Document(id=\"1\", page_content=\"apple\")\n",
|
||||
" d2 :Document = Document(id=\"2\", page_content=\"orange\")\n",
|
||||
" d3 :Document = Document(id=\"3\", page_content=\"tiger\")\n",
|
||||
" d4 :Document = Document(id=\"4\", page_content=\"cat\")\n",
|
||||
" d5 :Document = Document(id=\"5\", page_content=\"dog\")\n",
|
||||
" d6 :Document = Document(id=\"6\", page_content=\"fox\")\n",
|
||||
" d7 :Document = Document(id=\"7\", page_content=\"pear\")\n",
|
||||
" d8 :Document = Document(id=\"8\", page_content=\"banana\")\n",
|
||||
" d9 :Document = Document(id=\"9\", page_content=\"plum\")\n",
|
||||
" d10 :Document = Document(id=\"10\", page_content=\"lion\")\n",
|
||||
"\n",
|
||||
" documents = [d1, d2, d3, d4, d5, d6, d7, d8, d9, d10]\n",
|
||||
" return documents\n",
|
||||
"\n",
|
||||
"async def test_asimilarity_search_by_vector():\n",
|
||||
" documents = test_data()\n",
|
||||
" session: Session = await Session.create()\n",
|
||||
" try:\n",
|
||||
" named_map: NamedMap[str, Document] = await session.get_map(\"my-map\")\n",
|
||||
" embedding :Embeddings = HuggingFaceEmbeddings(\n",
|
||||
" model_name=\"sentence-transformers/all-MiniLM-l6-v2\")\n",
|
||||
" # this embedding generates vectors of dimension 384\n",
|
||||
" cvs :CoherenceVectorStore = await CoherenceVectorStore.create(\n",
|
||||
" named_map,embedding,384)\n",
|
||||
" await cvs.aadd_documents(documents)\n",
|
||||
" ids = [doc.id for doc in documents]\n",
|
||||
" l = await cvs.aget_by_ids(ids)\n",
|
||||
" assert len(l) == 10\n",
|
||||
"\n",
|
||||
" vector = cvs.embeddings.embed_query(\"fruit\")\n",
|
||||
" result = await cvs.asimilarity_search_by_vector(vector)\n",
|
||||
" assert len(result) == 4\n",
|
||||
" print(\"====\")\n",
|
||||
" for e in result:\n",
|
||||
" print(e)\n",
|
||||
" finally:\n",
|
||||
" await session.close()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "baee76cd-4a9a-4a4e-8a88-f54d9dd98790",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"jupytext": {
|
||||
"cell_metadata_filter": "-all",
|
||||
"main_language": "python",
|
||||
"notebook_metadata_filter": "-all"
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.21"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user