Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-18 09:25:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix flexible dimension and doc for DingoDB (#12187)

Browse Source
This commit is contained in:
Hech 2023-10-25 01:16:19 +08:00 committed by GitHub
parent 95ae40ff90
commit d76f026d72
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 18 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/api_reference/guide_imports.json
View File

File diff suppressed because one or more lines are too long

10
docs/docs/integrations/providers/dingo.mdx
View File

@ -1,14 +1,14 @@
# Dingo # DingoDB
This page covers how to use the Dingo ecosystem within LangChain. This page covers how to use the DingoDB ecosystem within LangChain.
It is broken into two parts: installation and setup, and then references to specific Dingo wrappers. It is broken into two parts: installation and setup, and then references to specific DingoDB wrappers.
## Installation and Setup ## Installation and Setup
- Install the Python SDK with `pip install dingodb` - Install the Python SDK with `pip install dingodb`
## VectorStore ## VectorStore
There exists a wrapper around Dingo indexes, allowing you to use it as a vectorstore, There exists a wrapper around DingoDB indexes, allowing you to use it as a vectorstore,
whether for semantic search or example selection. whether for semantic search or example selection.
To import this vectorstore: To import this vectorstore:
@ -16,4 +16,4 @@ To import this vectorstore:
from langchain.vectorstores import Dingo from langchain.vectorstores import Dingo
``` ```
For a more detailed walkthrough of the Dingo wrapper, see [this notebook](/docs/integrations/vectorstores/dingo.html) For a more detailed walkthrough of the DingoDB wrapper, see [this notebook](/docs/integrations/vectorstores/dingo.html)

4
docs/docs/integrations/vectorstores/dingo.ipynb
View File

@ -5,9 +5,9 @@
"id": "683953b3", "id": "683953b3",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Dingo\n", "# DingoDB\n",
"\n", "\n",
">[Dingo](https://dingodb.readthedocs.io/en/latest/) is a distributed multi-mode vector database, which combines the characteristics of data lakes and vector databases, and can store data of any type and size (Key-Value, PDF, audio, video, etc.). It has real-time low-latency processing capabilities to achieve rapid insight and response, and can efficiently conduct instant analysis and process multi-modal data.\n", ">[DingoDB](https://dingodb.readthedocs.io/en/latest/) is a distributed multi-mode vector database, which combines the characteristics of data lakes and vector databases, and can store data of any type and size (Key-Value, PDF, audio, video, etc.). It has real-time low-latency processing capabilities to achieve rapid insight and response, and can efficiently conduct instant analysis and process multi-modal data.\n",
"\n", "\n",
"This notebook shows how to use functionality related to the DingoDB vector database.\n", "This notebook shows how to use functionality related to the DingoDB vector database.\n",
"\n", "\n",

15
libs/langchain/langchain/vectorstores/dingo.py
View File

@ -36,6 +36,7 @@ class Dingo(VectorStore):
*, *,
client: Any = None, client: Any = None,
index_name: Optional[str] = None, index_name: Optional[str] = None,
dimension: int = 1024,
host: Optional[List[str]] = None, host: Optional[List[str]] = None,
user: str = "root", user: str = "root",
password: str = "123123", password: str = "123123",
@ -67,9 +68,11 @@ class Dingo(VectorStore):
if index_name is not None and index_name not in dingo_client.get_index(): if index_name is not None and index_name not in dingo_client.get_index():
if self_id is True: if self_id is True:
dingo_client.create_index(index_name, 1024, auto_id=False) dingo_client.create_index(
index_name, dimension=dimension, auto_id=False
)
else: else:
dingo_client.create_index(index_name, 1024) dingo_client.create_index(index_name, dimension=dimension)
self._index_name = index_name self._index_name = index_name
self._embedding = embedding self._embedding = embedding
@ -268,6 +271,7 @@ class Dingo(VectorStore):
ids: Optional[List[str]] = None, ids: Optional[List[str]] = None,
text_key: str = "text", text_key: str = "text",
index_name: Optional[str] = None, index_name: Optional[str] = None,
dimension: int = 1024,
client: Any = None, client: Any = None,
host: List[str] = ["172.20.31.10:13000"], host: List[str] = ["172.20.31.10:13000"],
user: str = "root", user: str = "root",
@ -315,11 +319,12 @@ class Dingo(VectorStore):
raise ValueError(f"Dingo failed to connect: {e}") raise ValueError(f"Dingo failed to connect: {e}")
if kwargs is not None and kwargs.get("self_id") is True: if kwargs is not None and kwargs.get("self_id") is True:
if index_name not in dingo_client.get_index(): if index_name not in dingo_client.get_index():
dingo_client.create_index(index_name, 1024, auto_id=False) dingo_client.create_index(
index_name, dimension=dimension, auto_id=False
)
else: else:
if index_name not in dingo_client.get_index(): if index_name not in dingo_client.get_index():
dingo_client.create_index(index_name, 1024) dingo_client.create_index(index_name, dimension=dimension)
# dingo_client.create_index(index_name, 1024, index_type="hnsw")
# Embed and create the documents # Embed and create the documents