github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-04-28 11:55:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs[patch]: Update kv store docs pages (#24848)

Browse Source
This commit is contained in:
Jacob Lee 2024-07-31 13:23:24 -07:00 committed by GitHub
parent 17a06cb7a6
commit 1213a59f87
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
12 changed files with 898 additions and 425 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/Makefile
View File

@ -42,6 +42,8 @@ generate-files:
$(PYTHON) scripts/document_loader_feat_table.py $(INTERMEDIATE_DIR)
$(PYTHON) scripts/kv_store_feat_table.py $(INTERMEDIATE_DIR)
$(PYTHON) scripts/partner_pkg_table.py $(INTERMEDIATE_DIR)
$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)

3
docs/docs/concepts.mdx
View File

@ -500,7 +500,8 @@ For specifics on how to use retrievers, see the [relevant how-to guides here](/d
### Key-value stores
For some techniques, such as [indexing and retrieval with multiple vectors per document](/docs/how_to/multi_vector/), having some sort of key-value (KV) storage is helpful.
For some techniques, such as [indexing and retrieval with multiple vectors per document](/docs/how_to/multi_vector/) or
[caching embeddings](/docs/how_to/caching_embeddings/), having a form of key-value (KV) storage is helpful.
LangChain includes a [`BaseStore`](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.BaseStore.html) interface,
which allows for storage of arbitrary data. However, LangChain components that require KV-storage accept a

272
docs/docs/integrations/stores/astradb.ipynb
View File

@ -2,10 +2,14 @@
"cells": [
{
"cell_type": "raw",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "raw"
}
},
"source": [
"---\n",
"sidebar_label: Astra DB\n",
"sidebar_label: AstraDB\n",
"---"
]
},
@ -13,130 +17,121 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"# Astra DB\n",
"# AstraDBByteStore\n",
"\n",
"This will help you get started with Astra DB [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `AstraDBByteStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain_astradb.storage.AstraDBByteStore.html).\n",
"\n",
"## Overview\n",
"\n",
"DataStax [Astra DB](https://docs.datastax.com/en/astra/home/astra.html) is a serverless vector-capable database built on Cassandra and made conveniently available through an easy-to-use JSON API.\n",
"\n",
"`AstraDBStore` and `AstraDBByteStore` need the `astrapy` package to be installed:"
"### Integration details\n",
"\n",
"| Class | Package | Local | JS support | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
"| [AstraDBByteStore](https://api.python.langchain.com/en/latest/storage/langchain_astradb.storage.AstraDBByteStore.html) | [langchain_astradb](https://api.python.langchain.com/en/latest/astradb_api_reference.html) | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_astradb?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_astradb?style=flat-square&label=%20) |\n",
"\n",
"## Setup\n",
"\n",
"To create an `AstraDBByteStore` byte store, you'll need to [create a DataStax account](https://www.datastax.com/products/datastax-astra).\n",
"\n",
"### Credentials\n",
"\n",
"After signing up, set the following credentials:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"vscode": {
"languageId": "plaintext"
}
},
"outputs": [],
"source": [
"%pip install --upgrade --quiet astrapy"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The Store takes the following parameters:\n",
"\n",
"* `api_endpoint`: Astra DB API endpoint. Looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`\n",
"* `token`: Astra DB token. Looks like `AstraCS:6gBhNmsk135....`\n",
"* `collection_name` : Astra DB collection name\n",
"* `namespace`: (Optional) Astra DB namespace"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## AstraDBStore\n",
"\n",
"The `AstraDBStore` is an implementation of `BaseStore` that stores everything in your DataStax Astra DB instance.\n",
"The store keys must be strings and will be mapped to the `_id` field of the Astra DB document.\n",
"The store values can be any object that can be serialized by `json.dumps`.\n",
"In the database, entries will have the form:\n",
"\n",
"```json\n",
"{\n",
" \"_id\": \"<key>\",\n",
" \"value\": <value>\n",
"}\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.storage import AstraDBStore"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from getpass import getpass\n",
"\n",
"ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n",
"ASTRA_DB_API_ENDPOINT = getpass(\"ASTRA_DB_API_ENDPOINT = \")\n",
"ASTRA_DB_APPLICATION_TOKEN = getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"The LangChain AstraDB integration lives in the `langchain_astradb` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"store = AstraDBStore(\n",
"%pip install -qU langchain_astradb"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our byte store:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"from langchain_astradb import AstraDBByteStore\n",
"\n",
"kv_store = AstraDBByteStore(\n",
" api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
" token=ASTRA_DB_APPLICATION_TOKEN,\n",
" collection_name=\"my_store\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['v1', [0.1, 0.2, 0.3]]\n"
]
}
],
"source": [
"store.mset([(\"k1\", \"v1\"), (\"k2\", [0.1, 0.2, 0.3])])\n",
"print(store.mget([\"k1\", \"k2\"]))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Usage with CacheBackedEmbeddings\n",
"## Usage\n",
"\n",
"You may use the `AstraDBStore` in conjunction with a [`CacheBackedEmbeddings`](/docs/how_to/caching_embeddings) to cache the result of embeddings computations.\n",
"Note that `AstraDBStore` stores the embeddings as a list of floats without converting them first to bytes so we don't use `fromByteStore` there."
"You can set data under keys like this using the `mset` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"[b'value1', b'value2']"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.embeddings import CacheBackedEmbeddings\n",
"from langchain_openai import OpenAIEmbeddings\n",
"kv_store.mset(\n",
" [\n",
" [\"key1\", b\"value1\"],\n",
" [\"key2\", b\"value2\"],\n",
" ]\n",
")\n",
"\n",
"embeddings = CacheBackedEmbeddings(\n",
" underlying_embeddings=OpenAIEmbeddings(), document_embedding_store=store\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
@ -144,96 +139,67 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## AstraDBByteStore\n",
"\n",
"The `AstraDBByteStore` is an implementation of `ByteStore` that stores everything in your DataStax Astra DB instance.\n",
"The store keys must be strings and will be mapped to the `_id` field of the Astra DB document.\n",
"The store `bytes` values are converted to base64 strings for storage into Astra DB.\n",
"In the database, entries will have the form:\n",
"\n",
"```json\n",
"{\n",
" \"_id\": \"<key>\",\n",
" \"value\": \"bytes encoded in base 64\"\n",
"}\n",
"```"
"And you can delete data using the `mdelete` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.storage import AstraDBByteStore"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from getpass import getpass\n",
"\n",
"ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n",
"ASTRA_DB_APPLICATION_TOKEN = getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"store = AstraDBByteStore(\n",
" api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
" token=ASTRA_DB_APPLICATION_TOKEN,\n",
" collection_name=\"my_store\",\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[b'v1', b'v2']\n"
]
"data": {
"text/plain": [
"[None, None]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
"print(store.mget([\"k1\", \"k2\"]))"
"kv_store.mdelete(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
"source": [
"You can use an `AstraDBByteStore` anywhere you'd use other ByteStores, including as a [cache for embeddings](/docs/how_to/caching_embeddings)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `AstraDBByteStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain_astradb.storage.AstraDBByteStore.html"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"display_name": "Python 3",
"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": "3.11.4"
"version": "3.10.5"
}
},
"nbformat": 4,

225
docs/docs/integrations/stores/cassandra.ipynb
View File

@ -2,7 +2,11 @@
"cells": [
{
"cell_type": "raw",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "raw"
}
},
"source": [
"---\n",
"sidebar_label: Cassandra\n",
@ -13,68 +17,62 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"# Cassandra\n",
"# CassandraByteStore\n",
"\n",
"This will help you get started with Cassandra [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `CassandraByteStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.cassandra.CassandraByteStore.html).\n",
"\n",
"## Overview\n",
"\n",
"[Cassandra](https://cassandra.apache.org/) is a NoSQL, row-oriented, highly scalable and highly available database.\n",
"\n",
"`CassandraByteStore` needs the `cassio` package to be installed:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"vscode": {
"languageId": "plaintext"
}
},
"outputs": [],
"source": [
"%pip install --upgrade --quiet cassio"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The Store takes the following parameters:\n",
"### Integration details\n",
"\n",
"* table: The table where to store the data.\n",
"* session: (Optional) The cassandra driver session. If not provided, the cassio resolved session will be used.\n",
"* keyspace: (Optional) The keyspace of the table. If not provided, the cassio resolved keyspace will be used.\n",
"* setup_mode: (Optional) The mode used to create the Cassandra table (SYNC, ASYNC or OFF). Defaults to SYNC."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## CassandraByteStore\n",
"| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/cassandra_storage) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
"| [CassandraByteStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.cassandra.CassandraByteStore.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_community?style=flat-square&label=%20) |\n",
"\n",
"## Setup\n",
"\n",
"The `CassandraByteStore` is an implementation of `ByteStore` that stores the data in your Cassandra instance.\n",
"The store keys must be strings and will be mapped to the `row_id` column of the Cassandra table.\n",
"The store `bytes` values are mapped to the `body_blob` column of the Cassandra table."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"The LangChain `CassandraByteStore` integration lives in the `langchain_community` package. You'll also need to install the `cassio` package or the `cassandra-driver` package as a peer dependency depending on which initialization method you're using:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.storage import CassandraByteStore"
"%pip install -qU langchain_community\n",
"%pip install -qU cassandra-driver\n",
"%pip install -qU cassio"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Init from a cassandra driver Session\n",
"You'll also need to create a `cassandra.cluster.Session` object, as described in the [Cassandra driver documentation](https://docs.datastax.com/en/developer/python-driver/latest/api/cassandra/cluster/#module-cassandra.cluster). The details vary (e.g. with network settings and authentication), but this might be something like:"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"You need to create a `cassandra.cluster.Session` object, as described in the [Cassandra driver documentation](https://docs.datastax.com/en/developer/python-driver/latest/api/cassandra/cluster/#module-cassandra.cluster). The details vary (e.g. with network settings and authentication), but this might be something like:"
],
"metadata": {
"collapsed": false
}
"You'll first need to create a `cassandra.cluster.Session` object, as described in the [Cassandra driver documentation](https://docs.datastax.com/en/developer/python-driver/latest/api/cassandra/cluster/#module-cassandra.cluster). The details vary (e.g. with network settings and authentication), but this might be something like:"
]
},
{
"cell_type": "code",
@ -90,12 +88,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You need to provide the name of an existing keyspace of the Cassandra instance:"
],
"metadata": {
"collapsed": false
}
"Then you can create your store! You'll also need to provide the name of an existing keyspace of the Cassandra instance:"
]
},
{
"cell_type": "code",
@ -103,61 +99,91 @@
"metadata": {},
"outputs": [],
"source": [
"CASSANDRA_KEYSPACE = input(\"CASSANDRA_KEYSPACE = \")"
"from langchain_community.storage import CassandraByteStore\n",
"\n",
"kv_store = CassandraByteStore(\n",
" table=\"my_store\",\n",
" session=session,\n",
" keyspace=\"<YOUR KEYSPACE>\",\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Creating the store:"
],
"metadata": {
"collapsed": false
}
"## Usage\n",
"\n",
"You can set data under keys like this using the `mset` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[b'v1', b'v2']\n"
]
}
],
"outputs": [],
"source": [
"store = CassandraByteStore(\n",
" table=\"my_store\",\n",
" session=session,\n",
" keyspace=CASSANDRA_KEYSPACE,\n",
"kv_store.mset(\n",
" [\n",
" [\"key1\", b\"value1\"],\n",
" [\"key2\", b\"value2\"],\n",
" ]\n",
")\n",
"\n",
"store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
"print(store.mget([\"k1\", \"k2\"]))"
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Init from cassio\n",
"\n",
"It's also possible to use cassio to configure the session and keyspace."
],
"metadata": {
"collapsed": false
}
"And you can delete data using the `mdelete` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"kv_store.mdelete(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Init using `cassio`\n",
"\n",
"It's also possible to use cassio to configure the session and keyspace."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import cassio\n",
"\n",
"cassio.init(contact_points=\"127.0.0.1\", keyspace=CASSANDRA_KEYSPACE)\n",
"cassio.init(contact_points=\"127.0.0.1\", keyspace=\"<YOUR KEYSPACE>\")\n",
"\n",
"store = CassandraByteStore(\n",
" table=\"my_store\",\n",
@ -165,62 +191,27 @@
"\n",
"store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
"print(store.mget([\"k1\", \"k2\"]))"
],
"metadata": {
"collapsed": false
}
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Usage with CacheBackedEmbeddings\n",
"## API reference\n",
"\n",
"You may use the `CassandraByteStore` in conjunction with a [`CacheBackedEmbeddings`](/docs/how_to/caching_embeddings) to cache the result of embeddings computations.\n"
],
"metadata": {
"collapsed": false
}
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [
"from langchain.embeddings import CacheBackedEmbeddings\n",
"from langchain_openai import OpenAIEmbeddings\n",
"\n",
"cassio.init(contact_points=\"127.0.0.1\", keyspace=CASSANDRA_KEYSPACE)\n",
"\n",
"store = CassandraByteStore(\n",
" table=\"my_store\",\n",
")\n",
"\n",
"embeddings = CacheBackedEmbeddings.from_bytes_store(\n",
" underlying_embeddings=OpenAIEmbeddings(), document_embedding_cache=store\n",
")"
],
"metadata": {
"collapsed": false
}
"For detailed documentation of all `CassandraByteStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain_community.storage.cassandra.CassandraByteStore.html"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"display_name": "Python 3",
"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": "3.11.4"
"version": "3.10.5"
}
},
"nbformat": 4,

185
docs/docs/integrations/stores/elasticsearch.ipynb
View File

@ -2,10 +2,14 @@
"cells": [
{
"cell_type": "raw",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "raw"
}
},
"source": [
"---\n",
"sidebar_label: Elasticsearch \n",
"sidebar_label: Elasticsearch\n",
"---"
]
},
@ -15,25 +19,31 @@
"source": [
"# ElasticsearchEmbeddingsCache\n",
"\n",
"This will help you get started with Elasticsearch [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `ElasticsearchEmbeddingsCache` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html).\n",
"\n",
"## Overview\n",
"\n",
"The `ElasticsearchEmbeddingsCache` is a `ByteStore` implementation that uses your Elasticsearch instance for efficient storage and retrieval of embeddings.\n",
"\n",
"### Integration details\n",
"\n",
"First install the LangChain integration with Elasticsearch."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install -U langchain-elasticsearch"
"| Class | Package | Local | JS support | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
"| [ElasticsearchEmbeddingsCache](https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html) | [langchain_elasticsearch](https://api.python.langchain.com/en/latest/elasticsearch_api_reference.html) | ✅ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_elasticsearch?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_elasticsearch?style=flat-square&label=%20) |\n",
"\n",
"## Setup\n",
"\n",
"To create a `ElasticsearchEmbeddingsCache` byte store, you'll need an Elasticsearch cluster. You can [set one up locally](https://www.elastic.co/downloads/elasticsearch) or create an [Elastic account](https://www.elastic.co/elasticsearch)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": "it can be instantiated using `CacheBackedEmbeddings.from_bytes_store` method."
"source": [
"### Installation\n",
"\n",
"The LangChain `ElasticsearchEmbeddingsCache` integration lives in the `__package_name__` package:"
]
},
{
"cell_type": "code",
@ -41,23 +51,37 @@
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings import CacheBackedEmbeddings\n",
"%pip install -qU langchain_elasticsearch"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our byte store:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"from langchain_elasticsearch import ElasticsearchEmbeddingsCache\n",
"from langchain_openai import OpenAIEmbeddings\n",
"\n",
"underlying_embeddings = OpenAIEmbeddings(model=\"text-embedding-3-small\")\n",
"\n",
"store = ElasticsearchEmbeddingsCache(\n",
" es_url=\"http://localhost:9200\",\n",
"# Example config for a locally running Elasticsearch instance\n",
"kv_store = ElasticsearchEmbeddingsCache(\n",
" es_url=\"https://localhost:9200\",\n",
" index_name=\"llm-chat-cache\",\n",
" metadata={\"project\": \"my_chatgpt_project\"},\n",
" namespace=\"my_chatgpt_project\",\n",
")\n",
"\n",
"embeddings = CacheBackedEmbeddings.from_bytes_store(\n",
" underlying_embeddings=OpenAIEmbeddings(),\n",
" document_embedding_cache=store,\n",
" query_embedding_cache=store,\n",
" es_user=\"elastic\",\n",
" es_password=\"<GENERATED PASSWORD>\",\n",
" es_params={\n",
" \"ca_certs\": \"~/http_ca.crt\",\n",
" },\n",
")"
]
},
@ -65,19 +89,93 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"The index_name parameter can also accept aliases. This allows to use the ILM: Manage the index lifecycle that we suggest to consider for managing retention and controlling cache growth.\n",
"## Usage\n",
"\n",
"Look at the class docstring for all parameters."
"You can set data under keys like this using the `mset` method:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[b'value1', b'value2']"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kv_store.mset(\n",
" [\n",
" [\"key1\", b\"value1\"],\n",
" [\"key2\", b\"value2\"],\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Index the generated vectors\n",
"The cached vectors won't be searchable by default. The developer can customize the building of the Elasticsearch document in order to add indexed vector field.\n",
"And you can delete data using the `mdelete` method:"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[None, None]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kv_store.mdelete(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")\n",
"\n",
"This can be done by subclassing end overriding methods. "
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Use as an embeddings cache\n",
"\n",
"Like other `ByteStores`, you can use an `ElasticsearchEmbeddingsCache` instance for [persistent caching in document ingestion](/docs/how_to/caching_embeddings/) for RAG.\n",
"\n",
"However, cached vectors won't be searchable by default. The developer can customize the building of the Elasticsearch document in order to add indexed vector field.\n",
"\n",
"This can be done by subclassing and overriding methods:"
]
},
{
@ -88,8 +186,6 @@
"source": [
"from typing import Any, Dict, List\n",
"\n",
"from langchain_elasticsearch import ElasticsearchEmbeddingsCache\n",
"\n",
"\n",
"class SearchableElasticsearchStore(ElasticsearchEmbeddingsCache):\n",
" @property\n",
@ -112,26 +208,29 @@
{
"cell_type": "markdown",
"metadata": {},
"source": "When overriding the mapping and the document building, please only make additive modifications, keeping the base mapping intact."
"source": [
"When overriding the mapping and the document building, please only make additive modifications, keeping the base mapping intact."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `ElasticsearchEmbeddingsCache` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"display_name": "Python 3",
"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": "3.11.4"
"version": "3.10.5"
}
},
"nbformat": 4,

178
docs/docs/integrations/stores/file_system.ipynb
View File

@ -2,11 +2,14 @@
"cells": [
{
"cell_type": "raw",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "raw"
}
},
"source": [
"---\n",
"sidebar_label: Local Filesystem\n",
"sidebar_position: 3\n",
"---"
]
},
@ -16,51 +19,119 @@
"source": [
"# LocalFileStore\n",
"\n",
"The `LocalFileStore` is a persistent implementation of `ByteStore` that stores everything in a folder of your choosing."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[b'v1', b'v2']\n"
]
}
],
"source": [
"from pathlib import Path\n",
"This will help you get started with local filesystem [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all LocalFileStore features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain.storage.file_system.LocalFileStore.html).\n",
"\n",
"from langchain.storage import LocalFileStore\n",
"## Overview\n",
"\n",
"root_path = Path.cwd() / \"data\" # can also be a path set by a string\n",
"store = LocalFileStore(root_path)\n",
"The `LocalFileStore` is a persistent implementation of `ByteStore` that stores everything in a folder of your choosing. It's useful if you're using a single machine and are tolerant of files being added or deleted.\n",
"\n",
"store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
"print(store.mget([\"k1\", \"k2\"]))"
"### Integration details\n",
"\n",
"| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/file_system) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
"| [LocalFileStore](https://api.python.langchain.com/en/latest/storage/langchain.storage.file_system.LocalFileStore.html) | [langchain](https://api.python.langchain.com/en/latest/langchain_api_reference.html) | ✅ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain?style=flat-square&label=%20) |"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now let's see which files exist in our `data` folder:"
"### Installation\n",
"\n",
"The LangChain `LocalFileStore` integration lives in the `langchain` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our byte store:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from pathlib import Path\n",
"\n",
"from langchain.storage import LocalFileStore\n",
"\n",
"root_path = Path.cwd() / \"data\" # can also be a path set by a string\n",
"\n",
"kv_store = LocalFileStore(root_path)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Usage\n",
"\n",
"You can set data under keys like this using the `mset` method:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[b'value1', b'value2']"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kv_store.mset(\n",
" [\n",
" [\"key1\", b\"value1\"],\n",
" [\"key2\", b\"value2\"],\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You can see the created files in your `data` folder:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"k1 k2\n"
"key1 key2\n"
]
}
],
@ -69,16 +140,57 @@
]
},
{
"cell_type": "code",
"execution_count": null,
"cell_type": "markdown",
"metadata": {},
"outputs": [],
"source": []
"source": [
"And you can delete data using the `mdelete` method:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[None, None]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kv_store.mdelete(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `LocalFileStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain.storage.file_system.LocalFileStore.html"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
@ -92,7 +204,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.10.5"
}
},
"nbformat": 4,

4
docs/docs/integrations/stores/in_memory.ipynb
View File

@ -9,7 +9,7 @@
},
"source": [
"---\n",
"sidebar_label: InMemoryByteStore\n",
"sidebar_label: In-memory\n",
"---"
]
},
@ -28,7 +28,7 @@
"### Integration details\n",
"\n",
"| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/in_memory/) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: | :---: |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
"| [InMemoryByteStore](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.InMemoryByteStore.html) | [langchain_core](https://api.python.langchain.com/en/latest/core_api_reference.html) | ✅ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_core?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_core?style=flat-square&label=%20) |"
]
},

12
docs/docs/integrations/stores/index.mdx
View File

@ -1,12 +0,0 @@
---
sidebar_position: 1
sidebar_class_name: hidden
---
# Key-value stores
[Key-value stores](/docs/concepts/#key-value-stores) are used by other LangChain components to store and retrieve data.
import DocCardList from "@theme/DocCardList";
<DocCardList />

153
docs/docs/integrations/stores/redis.ipynb
View File

@ -2,7 +2,11 @@
"cells": [
{
"cell_type": "raw",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "raw"
}
},
"source": [
"---\n",
"sidebar_label: Redis\n",
@ -15,9 +19,30 @@
"source": [
"# RedisStore\n",
"\n",
"This will help you get started with Redis [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `RedisStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.redis.RedisStore.html).\n",
"\n",
"## Overview\n",
"\n",
"The `RedisStore` is an implementation of `ByteStore` that stores everything in your Redis instance.\n",
"\n",
"To configure Redis, follow our [Redis guide](/docs/integrations/providers/redis)."
"### Integration details\n",
"\n",
"| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/ioredis_storage) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
"| [RedisStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.redis.RedisStore.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_community?style=flat-square&label=%20) |\n",
"\n",
"## Setup\n",
"\n",
"To create a Redis byte store, you'll need to set up a Redis instance. You can do this locally or via a provider - see our [Redis guide](/docs/integrations/providers/redis) for an overview of options."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"The LangChain `RedisStore` integration lives in the `langchain_community` package:"
]
},
{
@ -26,56 +51,128 @@
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet redis"
"%pip install -qU langchain_community redis"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our byte store:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[b'v1', b'v2']\n"
]
}
],
"outputs": [],
"source": [
"from langchain_community.storage import RedisStore\n",
"\n",
"store = RedisStore(redis_url=\"redis://localhost:6379\")\n",
"kv_store = RedisStore(redis_url=\"redis://localhost:6379\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Usage\n",
"\n",
"store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
"print(store.mget([\"k1\", \"k2\"]))"
"You can set data under keys like this using the `mset` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": []
"outputs": [
{
"data": {
"text/plain": [
"[b'value1', b'value2']"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kv_store.mset(\n",
" [\n",
" [\"key1\", b\"value1\"],\n",
" [\"key2\", b\"value2\"],\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"And you can delete data using the `mdelete` method:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[None, None]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kv_store.mdelete(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `RedisStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain_community.storage.redis.RedisStore.html"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"display_name": "Python 3",
"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": "3.11.4"
"version": "3.10.5"
}
},
"nbformat": 4,

178
docs/docs/integrations/stores/upstash_redis.ipynb
View File

@ -2,7 +2,11 @@
"cells": [
{
"cell_type": "raw",
"metadata": {},
"metadata": {
"vscode": {
"languageId": "raw"
}
},
"source": [
"---\n",
"sidebar_label: Upstash Redis\n",
@ -15,11 +19,48 @@
"source": [
"# UpstashRedisByteStore\n",
"\n",
"The `UpstashRedisStore` is an implementation of `ByteStore` that stores everything in your Upstash-hosted Redis instance.\n",
"This will help you get started with Upstash redis [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `UpstashRedisByteStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html).\n",
"\n",
"To use the base `RedisStore` instead, see [this guide](/docs/integrations/stores/redis/)\n",
"## Overview\n",
"\n",
"To configure Upstash Redis, follow our [Upstash guide](/docs/integrations/providers/upstash)."
"The `UpstashRedisStore` is an implementation of `ByteStore` that stores everything in your [Upstash](https://upstash.com/)-hosted Redis instance.\n",
"\n",
"To use the base `RedisStore` instead, see [this guide](/docs/integrations/stores/redis/).\n",
"\n",
"### Integration details\n",
"\n",
"| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/upstash_redis_storage) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
"| [UpstashRedisByteStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_community?style=flat-square&label=%20) |\n",
"\n",
"## Setup\n",
"\n",
"You'll first need to [sign up for an Upstash account](https://upstash.com/docs/redis/overall/getstarted). Next, you'll need to create a Redis database to connect to.\n",
"\n",
"### Credentials\n",
"\n",
"Once you've created your database, get your database URL (don't forget the `https://`!) and token:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from getpass import getpass\n",
"\n",
"URL = getpass(\"Enter your Upstash URL\")\n",
"TOKEN = getpass(\"Enter your Upstash REST token\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"The LangChain Upstash integration lives in the `langchain_community` package. You'll also need to install the `upstash-redis` package as a peer dependency:"
]
},
{
@ -28,61 +69,130 @@
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet upstash-redis"
"%pip install -qU langchain_community upstash-redis"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our byte store:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[b'v1', b'v2']\n"
]
}
],
"outputs": [],
"source": [
"from langchain_community.storage import UpstashRedisByteStore\n",
"from upstash_redis import Redis\n",
"\n",
"URL = \"<UPSTASH_REDIS_REST_URL>\"\n",
"TOKEN = \"<UPSTASH_REDIS_REST_TOKEN>\"\n",
"\n",
"redis_client = Redis(url=URL, token=TOKEN)\n",
"store = UpstashRedisByteStore(client=redis_client, ttl=None, namespace=\"test-ns\")\n",
"kv_store = UpstashRedisByteStore(client=redis_client, ttl=None, namespace=\"test-ns\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Usage\n",
"\n",
"store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
"print(store.mget([\"k1\", \"k2\"]))"
"You can set data under keys like this using the `mset` method:"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": []
"outputs": [
{
"data": {
"text/plain": [
"[b'value1', b'value2']"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kv_store.mset(\n",
" [\n",
" [\"key1\", b\"value1\"],\n",
" [\"key2\", b\"value2\"],\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"And you can delete data using the `mdelete` method:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[None, None]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"kv_store.mdelete(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")\n",
"\n",
"kv_store.mget(\n",
" [\n",
" \"key1\",\n",
" \"key2\",\n",
" ]\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `UpstashRedisByteStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"display_name": "Python 3",
"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": "3.11.4"
"version": "3.10.5"
}
},
"nbformat": 4,

107
docs/scripts/kv_store_feat_table.py Normal file
View File

@ -0,0 +1,107 @@
import sys
from pathlib import Path
from langchain_community import document_loaders
from langchain_core.document_loaders.base import BaseLoader
KV_STORE_TEMPLATE = """\
---
sidebar_class_name: hidden
keywords: [compatibility]
custom_edit_url:
hide_table_of_contents: true
---
# Key-value stores
[Key-value stores](/docs/concepts/#key-value-stores) are used by other LangChain components to store and retrieve data.
:::info
If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
:::
## Features
The following table shows information on all available key-value stores.
{table}
"""
KV_STORE_FEAT_TABLE = {
"AstraDBByteStore": {
"class": "[AstraDBByteStore](https://api.python.langchain.com/en/latest/storage/langchain_astradb.storage.AstraDBByteStore.html)",
"local": False,
"package": "[langchain_astradb](https://api.python.langchain.com/en/latest/astradb_api_reference.html)",
"downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_astradb?style=flat-square&label=%20)",
},
"CassandraByteStore": {
"class": "[CassandraByteStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.cassandra.CassandraByteStore.html)",
"local": False,
"package": "[langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html)",
"downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
},
"ElasticsearchEmbeddingsCache": {
"class": "[ElasticsearchEmbeddingsCache](https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html)",
"local": True,
"package": "[langchain_elasticsearch](https://api.python.langchain.com/en/latest/elasticsearch_api_reference.html)",
"downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_elasticsearch?style=flat-square&label=%20)",
},
"LocalFileStore": {
"class": "[LocalFileStore](https://api.python.langchain.com/en/latest/storage/langchain.storage.file_system.LocalFileStore.html)",
"local": True,
"package": "[langchain](https://api.python.langchain.com/en/latest/langchain_api_reference.html)",
"downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain?style=flat-square&label=%20)",
},
"InMemoryByteStore": {
"class": "[InMemoryByteStore](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.InMemoryByteStore.html)",
"local": True,
"package": "[langchain_core](https://api.python.langchain.com/en/latest/core_api_reference.html)",
"downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_core?style=flat-square&label=%20)",
},
"RedisStore": {
"class": "[RedisStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.redis.RedisStore.html)",
"local": True,
"package": "[langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html)",
"downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
},
"UpstashRedisByteStore": {
"class": "[UpstashRedisByteStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html)",
"local": False,
"package": "[langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html)",
"downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
},
}
DEPRECATED = []
def get_kv_store_table() -> str:
"""Get the table of KV stores."""
header = ["name", "package", "local", "downloads"]
title = ["Class", "Package", "Local", "Downloads"]
rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
for loader, feats in sorted(KV_STORE_FEAT_TABLE.items()):
if not feats or loader in DEPRECATED:
continue
rows += [
[feats["class"]]
+ ["✅" if feats.get(h) else "❌" for h in header[1:2]]
+ [feats["package"], feats["downloads"]]
]
return "\n".join(["|".join(row) for row in rows])
if __name__ == "__main__":
output_dir = Path(sys.argv[1])
output_integrations_dir = output_dir / "integrations"
output_integrations_dir_kv_stores = output_integrations_dir / "stores"
output_integrations_dir_kv_stores.mkdir(parents=True, exist_ok=True)
kv_stores_page = KV_STORE_TEMPLATE.format(table=get_kv_store_table())
with open(output_integrations_dir / "stores" / "index.mdx", "w") as f:
f.write(kv_stores_page)

4
libs/cli/langchain_cli/integration_template/docs/kv_store.ipynb
View File

@ -27,7 +27,7 @@
"\n",
"## Overview\n",
"\n",
"- TODO: (Optional) A short introduciton to the underlying technology/API.\n",
"- TODO: (Optional) A short introduction to the underlying technology/API.\n",
"\n",
"### Integration details\n",
"\n",
@ -36,7 +36,7 @@
"- TODO: Make sure API reference links are correct.\n",
"\n",
"| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/_package_name_) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: | :---: |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: |\n",
"| [__ModuleName__ByteStore](https://api.python.langchain.com/en/latest/stores/__module_name__.stores.__ModuleName__ByteStore.html) | [__package_name__](https://api.python.langchain.com/en/latest/__package_name_short_snake___api_reference.html) | ✅/❌ | ✅/❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/__package_name__?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/__package_name__?style=flat-square&label=%20) |\n",
"\n",
"## Setup\n",