mirror of https://github.com/hwchase17/langchain
Fix `make docs_build` and related scripts (#7276)
**Description: a description of the change**
Fixed `make docs_build` and related scripts which caused errors. There
are several changes.
First, I made the build of the documentation and the API Reference into
two separate commands. This is because it takes less time to build. The
commands for documents are `make docs_build`, `make docs_clean`, and
`make docs_linkcheck`. The commands for API Reference are `make
api_docs_build`, `api_docs_clean`, and `api_docs_linkcheck`.
It looked like `docs/.local_build.sh` could be used to build the
documentation, so I used that. Since `.local_build.sh` was also building
API Rerefence internally, I removed that process. `.local_build.sh` also
added some Bash options to stop in error or so. Futher more added `cd
"${SCRIPT_DIR}"` at the beginning so that the script will work no matter
which directory it is executed in.
`docs/api_reference/api_reference.rst` is removed, because which is
generated by `docs/api_reference/create_api_rst.py`, and added it to
.gitignore.
Finally, the description of CONTRIBUTING.md was modified.
**Issue: the issue # it fixes (if applicable)**
https://github.com/hwchase17/langchain/issues/6413
**Dependencies: any dependencies required for this change**
`nbdoc` was missing in group docs so it was added. I installed it with
the `poetry add --group docs nbdoc` command. I am concerned if any
modifications are needed to poetry.lock. I would greatly appreciate it
if you could pay close attention to this file during the review.
**Tag maintainer**
- General / Misc / if you don't know who to tag: @baskaryan
If this PR needs any additional changes, I'll be happy to make them!
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
pull/7077/head
os1ma
11 months ago
committed by
GitHub
parent
74c28df363
commit
2667ddc686
File diff suppressed because it is too large
Load Diff
@ -1,301 +1,303 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c94240f5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# GraphSparqlQAChain\n",
|
||||
"\n",
|
||||
"Graph databases are an excellent choice for applications based on network-like models. To standardize the syntax and semantics of such graphs, the W3C recommends Semantic Web Technologies, cp. [Semantic Web](https://www.w3.org/standards/semanticweb/). [SPARQL](https://www.w3.org/TR/sparql11-query/) serves as a query language analogously to SQL or Cypher for these graphs. This notebook demonstrates the application of LLMs as a natural language interface to a graph database by generating SPARQL.\\\n",
|
||||
"Disclaimer: To date, SPARQL query generation via LLMs is still a bit unstable. Be especially careful with UPDATE queries, which alter the graph."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "dbc0ee68",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"There are several sources you can run queries against, including files on the web, files you have available locally, SPARQL endpoints, e.g., [Wikidata](https://www.wikidata.org/wiki/Wikidata:Main_Page), and [triple stores](https://www.w3.org/wiki/LargeTripleStores)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "62812aad",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.chains import GraphSparqlQAChain\n",
|
||||
"from langchain.graphs import RdfGraph"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "0928915d",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"graph = RdfGraph(\n",
|
||||
" source_file=\"http://www.w3.org/People/Berners-Lee/card\",\n",
|
||||
" standard=\"rdf\",\n",
|
||||
" local_copy=\"test.ttl\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"Note that providing a `local_file` is necessary for storing changes locally if the source is read-only."
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "7af596b5"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "58c1a8ea",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Refresh graph schema information\n",
|
||||
"If the schema of the database changes, you can refresh the schema information needed to generate SPARQL queries."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "4e3de44f",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"graph.load_schema()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "1fe76ccd",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"In the following, each IRI is followed by the local name and optionally its description in parentheses. \n",
|
||||
"The RDF graph supports the following node types:\n",
|
||||
"<http://xmlns.com/foaf/0.1/PersonalProfileDocument> (PersonalProfileDocument, None), <http://www.w3.org/ns/auth/cert#RSAPublicKey> (RSAPublicKey, None), <http://www.w3.org/2000/10/swap/pim/contact#Male> (Male, None), <http://xmlns.com/foaf/0.1/Person> (Person, None), <http://www.w3.org/2006/vcard/ns#Work> (Work, None)\n",
|
||||
"The RDF graph supports the following relationships:\n",
|
||||
"<http://www.w3.org/2000/01/rdf-schema#seeAlso> (seeAlso, None), <http://purl.org/dc/elements/1.1/title> (title, None), <http://xmlns.com/foaf/0.1/mbox_sha1sum> (mbox_sha1sum, None), <http://xmlns.com/foaf/0.1/maker> (maker, None), <http://www.w3.org/ns/solid/terms#oidcIssuer> (oidcIssuer, None), <http://www.w3.org/2000/10/swap/pim/contact#publicHomePage> (publicHomePage, None), <http://xmlns.com/foaf/0.1/openid> (openid, None), <http://www.w3.org/ns/pim/space#storage> (storage, None), <http://xmlns.com/foaf/0.1/name> (name, None), <http://www.w3.org/2000/10/swap/pim/contact#country> (country, None), <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> (type, None), <http://www.w3.org/ns/solid/terms#profileHighlightColor> (profileHighlightColor, None), <http://www.w3.org/ns/pim/space#preferencesFile> (preferencesFile, None), <http://www.w3.org/2000/01/rdf-schema#label> (label, None), <http://www.w3.org/ns/auth/cert#modulus> (modulus, None), <http://www.w3.org/2000/10/swap/pim/contact#participant> (participant, None), <http://www.w3.org/2000/10/swap/pim/contact#street2> (street2, None), <http://www.w3.org/2006/vcard/ns#locality> (locality, None), <http://xmlns.com/foaf/0.1/nick> (nick, None), <http://xmlns.com/foaf/0.1/homepage> (homepage, None), <http://creativecommons.org/ns#license> (license, None), <http://xmlns.com/foaf/0.1/givenname> (givenname, None), <http://www.w3.org/2006/vcard/ns#street-address> (street-address, None), <http://www.w3.org/2006/vcard/ns#postal-code> (postal-code, None), <http://www.w3.org/2000/10/swap/pim/contact#street> (street, None), <http://www.w3.org/2003/01/geo/wgs84_pos#lat> (lat, None), <http://xmlns.com/foaf/0.1/primaryTopic> (primaryTopic, None), <http://www.w3.org/2006/vcard/ns#fn> (fn, None), <http://www.w3.org/2003/01/geo/wgs84_pos#location> (location, None), <http://usefulinc.com/ns/doap#developer> (developer, None), <http://www.w3.org/2000/10/swap/pim/contact#city> (city, None), <http://www.w3.org/2006/vcard/ns#region> (region, None), <http://xmlns.com/foaf/0.1/member> (member, None), <http://www.w3.org/2003/01/geo/wgs84_pos#long> (long, None), <http://www.w3.org/2000/10/swap/pim/contact#address> (address, None), <http://xmlns.com/foaf/0.1/family_name> (family_name, None), <http://xmlns.com/foaf/0.1/account> (account, None), <http://xmlns.com/foaf/0.1/workplaceHomepage> (workplaceHomepage, None), <http://purl.org/dc/terms/title> (title, None), <http://www.w3.org/ns/solid/terms#publicTypeIndex> (publicTypeIndex, None), <http://www.w3.org/2000/10/swap/pim/contact#office> (office, None), <http://www.w3.org/2000/10/swap/pim/contact#homePage> (homePage, None), <http://xmlns.com/foaf/0.1/mbox> (mbox, None), <http://www.w3.org/2000/10/swap/pim/contact#preferredURI> (preferredURI, None), <http://www.w3.org/ns/solid/terms#profileBackgroundColor> (profileBackgroundColor, None), <http://schema.org/owns> (owns, None), <http://xmlns.com/foaf/0.1/based_near> (based_near, None), <http://www.w3.org/2006/vcard/ns#hasAddress> (hasAddress, None), <http://xmlns.com/foaf/0.1/img> (img, None), <http://www.w3.org/2000/10/swap/pim/contact#assistant> (assistant, None), <http://xmlns.com/foaf/0.1/title> (title, None), <http://www.w3.org/ns/auth/cert#key> (key, None), <http://www.w3.org/ns/ldp#inbox> (inbox, None), <http://www.w3.org/ns/solid/terms#editableProfile> (editableProfile, None), <http://www.w3.org/2000/10/swap/pim/contact#postalCode> (postalCode, None), <http://xmlns.com/foaf/0.1/weblog> (weblog, None), <http://www.w3.org/ns/auth/cert#exponent> (exponent, None), <http://rdfs.org/sioc/ns#avatar> (avatar, None)\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"graph.get_schema"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "68a3c677",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Querying the graph\n",
|
||||
"\n",
|
||||
"Now, you can use the graph SPARQL QA chain to ask questions about the graph."
|
||||
]
|
||||
},
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c94240f5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# GraphSparqlQAChain\n",
|
||||
"\n",
|
||||
"Graph databases are an excellent choice for applications based on network-like models. To standardize the syntax and semantics of such graphs, the W3C recommends Semantic Web Technologies, cp. [Semantic Web](https://www.w3.org/standards/semanticweb/). [SPARQL](https://www.w3.org/TR/sparql11-query/) serves as a query language analogously to SQL or Cypher for these graphs. This notebook demonstrates the application of LLMs as a natural language interface to a graph database by generating SPARQL.\\\n",
|
||||
"Disclaimer: To date, SPARQL query generation via LLMs is still a bit unstable. Be especially careful with UPDATE queries, which alter the graph."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "dbc0ee68",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"There are several sources you can run queries against, including files on the web, files you have available locally, SPARQL endpoints, e.g., [Wikidata](https://www.wikidata.org/wiki/Wikidata:Main_Page), and [triple stores](https://www.w3.org/wiki/LargeTripleStores)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "62812aad",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.chains import GraphSparqlQAChain\n",
|
||||
"from langchain.graphs import RdfGraph"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "0928915d",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"graph = RdfGraph(\n",
|
||||
" source_file=\"http://www.w3.org/People/Berners-Lee/card\",\n",
|
||||
" standard=\"rdf\",\n",
|
||||
" local_copy=\"test.ttl\",\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"Note that providing a `local_file` is necessary for storing changes locally if the source is read-only."
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"id": "7af596b5"
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "58c1a8ea",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Refresh graph schema information\n",
|
||||
"If the schema of the database changes, you can refresh the schema information needed to generate SPARQL queries."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "4e3de44f",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"graph.load_schema()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "1fe76ccd",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "7476ce98",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = GraphSparqlQAChain.from_llm(\n",
|
||||
" ChatOpenAI(temperature=0), graph=graph, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"In the following, each IRI is followed by the local name and optionally its description in parentheses. \n",
|
||||
"The RDF graph supports the following node types:\n",
|
||||
"<http://xmlns.com/foaf/0.1/PersonalProfileDocument> (PersonalProfileDocument, None), <http://www.w3.org/ns/auth/cert#RSAPublicKey> (RSAPublicKey, None), <http://www.w3.org/2000/10/swap/pim/contact#Male> (Male, None), <http://xmlns.com/foaf/0.1/Person> (Person, None), <http://www.w3.org/2006/vcard/ns#Work> (Work, None)\n",
|
||||
"The RDF graph supports the following relationships:\n",
|
||||
"<http://www.w3.org/2000/01/rdf-schema#seeAlso> (seeAlso, None), <http://purl.org/dc/elements/1.1/title> (title, None), <http://xmlns.com/foaf/0.1/mbox_sha1sum> (mbox_sha1sum, None), <http://xmlns.com/foaf/0.1/maker> (maker, None), <http://www.w3.org/ns/solid/terms#oidcIssuer> (oidcIssuer, None), <http://www.w3.org/2000/10/swap/pim/contact#publicHomePage> (publicHomePage, None), <http://xmlns.com/foaf/0.1/openid> (openid, None), <http://www.w3.org/ns/pim/space#storage> (storage, None), <http://xmlns.com/foaf/0.1/name> (name, None), <http://www.w3.org/2000/10/swap/pim/contact#country> (country, None), <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> (type, None), <http://www.w3.org/ns/solid/terms#profileHighlightColor> (profileHighlightColor, None), <http://www.w3.org/ns/pim/space#preferencesFile> (preferencesFile, None), <http://www.w3.org/2000/01/rdf-schema#label> (label, None), <http://www.w3.org/ns/auth/cert#modulus> (modulus, None), <http://www.w3.org/2000/10/swap/pim/contact#participant> (participant, None), <http://www.w3.org/2000/10/swap/pim/contact#street2> (street2, None), <http://www.w3.org/2006/vcard/ns#locality> (locality, None), <http://xmlns.com/foaf/0.1/nick> (nick, None), <http://xmlns.com/foaf/0.1/homepage> (homepage, None), <http://creativecommons.org/ns#license> (license, None), <http://xmlns.com/foaf/0.1/givenname> (givenname, None), <http://www.w3.org/2006/vcard/ns#street-address> (street-address, None), <http://www.w3.org/2006/vcard/ns#postal-code> (postal-code, None), <http://www.w3.org/2000/10/swap/pim/contact#street> (street, None), <http://www.w3.org/2003/01/geo/wgs84_pos#lat> (lat, None), <http://xmlns.com/foaf/0.1/primaryTopic> (primaryTopic, None), <http://www.w3.org/2006/vcard/ns#fn> (fn, None), <http://www.w3.org/2003/01/geo/wgs84_pos#location> (location, None), <http://usefulinc.com/ns/doap#developer> (developer, None), <http://www.w3.org/2000/10/swap/pim/contact#city> (city, None), <http://www.w3.org/2006/vcard/ns#region> (region, None), <http://xmlns.com/foaf/0.1/member> (member, None), <http://www.w3.org/2003/01/geo/wgs84_pos#long> (long, None), <http://www.w3.org/2000/10/swap/pim/contact#address> (address, None), <http://xmlns.com/foaf/0.1/family_name> (family_name, None), <http://xmlns.com/foaf/0.1/account> (account, None), <http://xmlns.com/foaf/0.1/workplaceHomepage> (workplaceHomepage, None), <http://purl.org/dc/terms/title> (title, None), <http://www.w3.org/ns/solid/terms#publicTypeIndex> (publicTypeIndex, None), <http://www.w3.org/2000/10/swap/pim/contact#office> (office, None), <http://www.w3.org/2000/10/swap/pim/contact#homePage> (homePage, None), <http://xmlns.com/foaf/0.1/mbox> (mbox, None), <http://www.w3.org/2000/10/swap/pim/contact#preferredURI> (preferredURI, None), <http://www.w3.org/ns/solid/terms#profileBackgroundColor> (profileBackgroundColor, None), <http://schema.org/owns> (owns, None), <http://xmlns.com/foaf/0.1/based_near> (based_near, None), <http://www.w3.org/2006/vcard/ns#hasAddress> (hasAddress, None), <http://xmlns.com/foaf/0.1/img> (img, None), <http://www.w3.org/2000/10/swap/pim/contact#assistant> (assistant, None), <http://xmlns.com/foaf/0.1/title> (title, None), <http://www.w3.org/ns/auth/cert#key> (key, None), <http://www.w3.org/ns/ldp#inbox> (inbox, None), <http://www.w3.org/ns/solid/terms#editableProfile> (editableProfile, None), <http://www.w3.org/2000/10/swap/pim/contact#postalCode> (postalCode, None), <http://xmlns.com/foaf/0.1/weblog> (weblog, None), <http://www.w3.org/ns/auth/cert#exponent> (exponent, None), <http://rdfs.org/sioc/ns#avatar> (avatar, None)\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"graph.get_schema"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "68a3c677",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Querying the graph\n",
|
||||
"\n",
|
||||
"Now, you can use the graph SPARQL QA chain to ask questions about the graph."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "7476ce98",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = GraphSparqlQAChain.from_llm(\n",
|
||||
" ChatOpenAI(temperature=0), graph=graph, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "ef8ee27b",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "ef8ee27b",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new GraphSparqlQAChain chain...\u001b[0m\n",
|
||||
"Identified intent:\n",
|
||||
"\u001b[32;1m\u001b[1;3mSELECT\u001b[0m\n",
|
||||
"Generated SPARQL:\n",
|
||||
"\u001b[32;1m\u001b[1;3mPREFIX foaf: <http://xmlns.com/foaf/0.1/>\n",
|
||||
"SELECT ?homepage\n",
|
||||
"WHERE {\n",
|
||||
" ?person foaf:name \"Tim Berners-Lee\" .\n",
|
||||
" ?person foaf:workplaceHomepage ?homepage .\n",
|
||||
"}\u001b[0m\n",
|
||||
"Full Context:\n",
|
||||
"\u001b[32;1m\u001b[1;3m[]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Tim Berners-Lee's work homepage is http://www.w3.org/People/Berners-Lee/.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.run(\"What is Tim Berners-Lee's work homepage?\")"
|
||||
]
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new GraphSparqlQAChain chain...\u001b[0m\n",
|
||||
"Identified intent:\n",
|
||||
"\u001b[32;1m\u001b[1;3mSELECT\u001b[0m\n",
|
||||
"Generated SPARQL:\n",
|
||||
"\u001b[32;1m\u001b[1;3mPREFIX foaf: <http://xmlns.com/foaf/0.1/>\n",
|
||||
"SELECT ?homepage\n",
|
||||
"WHERE {\n",
|
||||
" ?person foaf:name \"Tim Berners-Lee\" .\n",
|
||||
" ?person foaf:workplaceHomepage ?homepage .\n",
|
||||
"}\u001b[0m\n",
|
||||
"Full Context:\n",
|
||||
"\u001b[32;1m\u001b[1;3m[]\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "af4b3294",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Updating the graph\n",
|
||||
"\n",
|
||||
"Analogously, you can update the graph, i.e., insert triples, using natural language."
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Tim Berners-Lee's work homepage is http://www.w3.org/People/Berners-Lee/.\""
|
||||
]
|
||||
},
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.run(\"What is Tim Berners-Lee's work homepage?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "af4b3294",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Updating the graph\n",
|
||||
"\n",
|
||||
"Analogously, you can update the graph, i.e., insert triples, using natural language."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "fdf38841",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "fdf38841",
|
||||
"metadata": {
|
||||
"pycharm": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new GraphSparqlQAChain chain...\u001b[0m\n",
|
||||
"Identified intent:\n",
|
||||
"\u001b[32;1m\u001b[1;3mUPDATE\u001b[0m\n",
|
||||
"Generated SPARQL:\n",
|
||||
"\u001b[32;1m\u001b[1;3mPREFIX foaf: <http://xmlns.com/foaf/0.1/>\n",
|
||||
"INSERT {\n",
|
||||
" ?person foaf:workplaceHomepage <http://www.w3.org/foo/bar/> .\n",
|
||||
"}\n",
|
||||
"WHERE {\n",
|
||||
" ?person foaf:name \"Timothy Berners-Lee\" .\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Successfully inserted triples into the graph.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.run(\"Save that the person with the name 'Timothy Berners-Lee' has a work homepage at 'http://www.w3.org/foo/bar/'\")"
|
||||
]
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new GraphSparqlQAChain chain...\u001b[0m\n",
|
||||
"Identified intent:\n",
|
||||
"\u001b[32;1m\u001b[1;3mUPDATE\u001b[0m\n",
|
||||
"Generated SPARQL:\n",
|
||||
"\u001b[32;1m\u001b[1;3mPREFIX foaf: <http://xmlns.com/foaf/0.1/>\n",
|
||||
"INSERT {\n",
|
||||
" ?person foaf:workplaceHomepage <http://www.w3.org/foo/bar/> .\n",
|
||||
"}\n",
|
||||
"WHERE {\n",
|
||||
" ?person foaf:name \"Timothy Berners-Lee\" .\n",
|
||||
"}\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5e0f7fc1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's verify the results:"
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Successfully inserted triples into the graph.'"
|
||||
]
|
||||
},
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.run(\n",
|
||||
" \"Save that the person with the name 'Timothy Berners-Lee' has a work homepage at 'http://www.w3.org/foo/bar/'\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5e0f7fc1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's verify the results:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "f874171b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "f874171b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[(rdflib.term.URIRef('https://www.w3.org/'),),\n",
|
||||
" (rdflib.term.URIRef('http://www.w3.org/foo/bar/'),)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"query = (\n",
|
||||
" \"\"\"PREFIX foaf: <http://xmlns.com/foaf/0.1/>\\n\"\"\"\n",
|
||||
" \"\"\"SELECT ?hp\\n\"\"\"\n",
|
||||
" \"\"\"WHERE {\\n\"\"\"\n",
|
||||
" \"\"\" ?person foaf:name \"Timothy Berners-Lee\" . \\n\"\"\"\n",
|
||||
" \"\"\" ?person foaf:workplaceHomepage ?hp .\\n\"\"\"\n",
|
||||
" \"\"\"}\"\"\"\n",
|
||||
")\n",
|
||||
"graph.query(query)"
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[(rdflib.term.URIRef('https://www.w3.org/'),),\n",
|
||||
" (rdflib.term.URIRef('http://www.w3.org/foo/bar/'),)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "lc",
|
||||
"language": "python",
|
||||
"name": "lc"
|
||||
},
|
||||
"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"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"query = (\n",
|
||||
" \"\"\"PREFIX foaf: <http://xmlns.com/foaf/0.1/>\\n\"\"\"\n",
|
||||
" \"\"\"SELECT ?hp\\n\"\"\"\n",
|
||||
" \"\"\"WHERE {\\n\"\"\"\n",
|
||||
" \"\"\" ?person foaf:name \"Timothy Berners-Lee\" . \\n\"\"\"\n",
|
||||
" \"\"\" ?person foaf:workplaceHomepage ?hp .\\n\"\"\"\n",
|
||||
" \"\"\"}\"\"\"\n",
|
||||
")\n",
|
||||
"graph.query(query)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "lc",
|
||||
"language": "python",
|
||||
"name": "lc"
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
"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"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@ -1,243 +1,199 @@
|
||||
{
|
||||
"cells":[
|
||||
{
|
||||
"attachments":{
|
||||
|
||||
},
|
||||
"cell_type":"markdown",
|
||||
"id":"683953b3",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"source":[
|
||||
"# MongoDB Atlas\n",
|
||||
"\n",
|
||||
">[MongoDB Atlas](https://www.mongodb.com/docs/atlas/) is a fully-managed cloud database available in AWS , Azure, and GCP. It now has support for native Vector Search on your MongoDB document data.\n",
|
||||
"\n",
|
||||
"This notebook shows how to use `MongoDB Atlas Vector Search` to store your embeddings in MongoDB documents, create a vector search index, and perform KNN search with an approximate nearest neighbor algorithm.\n",
|
||||
"\n",
|
||||
"It uses the [knnBeta Operator](https://www.mongodb.com/docs/atlas/atlas-search/knn-beta) available in MongoDB Atlas Search. This feature is in Public Preview and available for evaluation purposes, to validate functionality, and to gather feedback from public preview users. It is not recommended for production deployments as we may introduce breaking changes.\n",
|
||||
"\n",
|
||||
"To use MongoDB Atlas, you must first deploy a cluster. We have a Forever-Free tier of clusters available. \n",
|
||||
"To get started head over to Atlas here: [quick start](https://www.mongodb.com/docs/atlas/getting-started/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type":"code",
|
||||
"execution_count":null,
|
||||
"id":"b4c41cad-08ef-4f72-a545-2151e4598efe",
|
||||
"metadata":{
|
||||
"tags":[
|
||||
|
||||
]
|
||||
},
|
||||
"outputs":[
|
||||
|
||||
],
|
||||
"source":[
|
||||
"!pip install pymongo"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type":"code",
|
||||
"execution_count":null,
|
||||
"id":"c1e38361-c1fe-4ac6-86e9-c90ebaf7ae87",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"outputs":[
|
||||
|
||||
],
|
||||
"source":[
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"MONGODB_ATLAS_CLUSTER_URI = getpass.getpass(\"MongoDB Atlas Cluster URI:\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments":{
|
||||
|
||||
},
|
||||
"cell_type":"markdown",
|
||||
"id":"457ace44-1d95-4001-9dd5-78811ab208ad",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"source":[
|
||||
"We want to use `OpenAIEmbeddings` so we need to set up our OpenAI API Key. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type":"code",
|
||||
"execution_count":null,
|
||||
"id":"2d8f240d",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"outputs":[
|
||||
|
||||
],
|
||||
"source":[
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments":{
|
||||
|
||||
},
|
||||
"cell_type":"markdown",
|
||||
"id":"1f3ecc42",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"source":[
|
||||
"Now, let's create a vector search index on your cluster. In the below example, `embedding` is the name of the field that contains the embedding vector. Please refer to the [documentation](https://www.mongodb.com/docs/atlas/atlas-search/define-field-mappings-for-vector-search) to get more details on how to define an Atlas Vector Search index.\n",
|
||||
"You can name the index `langchain_demo` and create the index on the namespace `lanchain_db.langchain_col`. Finally, write the following definition in the JSON editor on MongoDB Atlas:\n",
|
||||
"\n",
|
||||
"```json\n",
|
||||
"{\n",
|
||||
" \"mappings\": {\n",
|
||||
" \"dynamic\": true,\n",
|
||||
" \"fields\": {\n",
|
||||
" \"embedding\": {\n",
|
||||
" \"dimensions\": 1536,\n",
|
||||
" \"similarity\": \"cosine\",\n",
|
||||
" \"type\": \"knnVector\"\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
"}\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type":"code",
|
||||
"execution_count":2,
|
||||
"id":"aac9563e",
|
||||
"metadata":{
|
||||
"tags":[
|
||||
|
||||
]
|
||||
},
|
||||
"outputs":[
|
||||
|
||||
],
|
||||
"source":[
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.vectorstores import MongoDBAtlasVectorSearch\n",
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"\n",
|
||||
"loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"docs = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type":"code",
|
||||
"execution_count":null,
|
||||
"id":"6e104aee",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"outputs":[
|
||||
|
||||
],
|
||||
"source":[
|
||||
"from pymongo import MongoClient\n",
|
||||
"\n",
|
||||
"# initialize MongoDB python client\n",
|
||||
"client = MongoClient(MONGODB_ATLAS_CLUSTER_URI)\n",
|
||||
"\n",
|
||||
"db_name = \"langchain_db\"\n",
|
||||
"collection_name = \"langchain_col\"\n",
|
||||
"collection = client[db_name][collection_name]\n",
|
||||
"index_name = \"langchain_demo\"\n",
|
||||
"\n",
|
||||
"# insert the documents in MongoDB Atlas with their embedding\n",
|
||||
"docsearch = MongoDBAtlasVectorSearch.from_documents(\n",
|
||||
" docs, embeddings, collection=collection, index_name=index_name\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# perform a similarity search between the embedding of the query and the embeddings of the documents\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = docsearch.similarity_search(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type":"code",
|
||||
"execution_count":null,
|
||||
"id":"9c608226",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"outputs":[
|
||||
|
||||
],
|
||||
"source":[
|
||||
"print(docs[0].page_content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments":{
|
||||
|
||||
},
|
||||
"cell_type":"markdown",
|
||||
"id":"851a2ec9-9390-49a4-8412-3e132c9f789d",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"source":[
|
||||
"You can also instantiate the vector store directly and execute a query as follows:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type":"code",
|
||||
"execution_count":null,
|
||||
"id":"6336fe79-3e73-48be-b20a-0ff1bb6a4399",
|
||||
"metadata":{
|
||||
|
||||
},
|
||||
"outputs":[
|
||||
|
||||
],
|
||||
"source":[
|
||||
"# initialize vector store\n",
|
||||
"vectorstore = MongoDBAtlasVectorSearch(\n",
|
||||
" collection, OpenAIEmbeddings(), index_name=index_name\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# perform a similarity search between a query and the ingested documents\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = vectorstore.similarity_search(query)\n",
|
||||
"\n",
|
||||
"print(docs[0].page_content)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata":{
|
||||
"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":"3.10.6"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "683953b3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# MongoDB Atlas\n",
|
||||
"\n",
|
||||
">[MongoDB Atlas](https://www.mongodb.com/docs/atlas/) is a fully-managed cloud database available in AWS , Azure, and GCP. It now has support for native Vector Search on your MongoDB document data.\n",
|
||||
"\n",
|
||||
"This notebook shows how to use `MongoDB Atlas Vector Search` to store your embeddings in MongoDB documents, create a vector search index, and perform KNN search with an approximate nearest neighbor algorithm.\n",
|
||||
"\n",
|
||||
"It uses the [knnBeta Operator](https://www.mongodb.com/docs/atlas/atlas-search/knn-beta) available in MongoDB Atlas Search. This feature is in Public Preview and available for evaluation purposes, to validate functionality, and to gather feedback from public preview users. It is not recommended for production deployments as we may introduce breaking changes.\n",
|
||||
"\n",
|
||||
"To use MongoDB Atlas, you must first deploy a cluster. We have a Forever-Free tier of clusters available. \n",
|
||||
"To get started head over to Atlas here: [quick start](https://www.mongodb.com/docs/atlas/getting-started/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b4c41cad-08ef-4f72-a545-2151e4598efe",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"nbformat":4,
|
||||
"nbformat_minor":5
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install pymongo"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "c1e38361-c1fe-4ac6-86e9-c90ebaf7ae87",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"MONGODB_ATLAS_CLUSTER_URI = getpass.getpass(\"MongoDB Atlas Cluster URI:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "457ace44-1d95-4001-9dd5-78811ab208ad",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We want to use `OpenAIEmbeddings` so we need to set up our OpenAI API Key. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "2d8f240d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "1f3ecc42",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now, let's create a vector search index on your cluster. In the below example, `embedding` is the name of the field that contains the embedding vector. Please refer to the [documentation](https://www.mongodb.com/docs/atlas/atlas-search/define-field-mappings-for-vector-search) to get more details on how to define an Atlas Vector Search index.\n",
|
||||
"You can name the index `langchain_demo` and create the index on the namespace `lanchain_db.langchain_col`. Finally, write the following definition in the JSON editor on MongoDB Atlas:\n",
|
||||
"\n",
|
||||
"```json\n",
|
||||
"{\n",
|
||||
" \"mappings\": {\n",
|
||||
" \"dynamic\": true,\n",
|
||||
" \"fields\": {\n",
|
||||
" \"embedding\": {\n",
|
||||
" \"dimensions\": 1536,\n",
|
||||
" \"similarity\": \"cosine\",\n",
|
||||
" \"type\": \"knnVector\"\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
"}\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "aac9563e",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.vectorstores import MongoDBAtlasVectorSearch\n",
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"\n",
|
||||
"loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"docs = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6e104aee",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from pymongo import MongoClient\n",
|
||||
"\n",
|
||||
"# initialize MongoDB python client\n",
|
||||
"client = MongoClient(MONGODB_ATLAS_CLUSTER_URI)\n",
|
||||
"\n",
|
||||
"db_name = \"langchain_db\"\n",
|
||||
"collection_name = \"langchain_col\"\n",
|
||||
"collection = client[db_name][collection_name]\n",
|
||||
"index_name = \"langchain_demo\"\n",
|
||||
"\n",
|
||||
"# insert the documents in MongoDB Atlas with their embedding\n",
|
||||
"docsearch = MongoDBAtlasVectorSearch.from_documents(\n",
|
||||
" docs, embeddings, collection=collection, index_name=index_name\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# perform a similarity search between the embedding of the query and the embeddings of the documents\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = docsearch.similarity_search(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9c608226",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(docs[0].page_content)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "851a2ec9-9390-49a4-8412-3e132c9f789d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can also instantiate the vector store directly and execute a query as follows:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6336fe79-3e73-48be-b20a-0ff1bb6a4399",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# initialize vector store\n",
|
||||
"vectorstore = MongoDBAtlasVectorSearch(\n",
|
||||
" collection, OpenAIEmbeddings(), index_name=index_name\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# perform a similarity search between a query and the ingested documents\n",
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
"docs = vectorstore.similarity_search(query)\n",
|
||||
"\n",
|
||||
"print(docs[0].page_content)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"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": "3.10.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue