mirror of https://github.com/hwchase17/langchain
docs `integrations/providers` update 10 (#19970)
Fixed broken links. Formatted to get consistent forms. Added missed imports in the example codepull/19941/head^2
Leonid Ganeline
5 months ago
committed by
GitHub
parent
82f0198be2
commit
4c969286fe
@ -1,22 +1,23 @@
|
||||
# Tair
|
||||
|
||||
This page covers how to use the Tair ecosystem within LangChain.
|
||||
>[Alibaba Cloud Tair](https://www.alibabacloud.com/help/en/tair/latest/what-is-tair) is a cloud native in-memory database service
|
||||
> developed by `Alibaba Cloud`. It provides rich data models and enterprise-grade capabilities to
|
||||
> support your real-time online scenarios while maintaining full compatibility with open-source `Redis`.
|
||||
> `Tair` also introduces persistent memory-optimized instances that are based on
|
||||
> new non-volatile memory (NVM) storage medium.
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
Install Tair Python SDK with `pip install tair`.
|
||||
Install Tair Python SDK:
|
||||
|
||||
## Wrappers
|
||||
|
||||
### VectorStore
|
||||
|
||||
There exists a wrapper around TairVector, allowing you to use it as a vectorstore,
|
||||
whether for semantic search or example selection.
|
||||
```bash
|
||||
pip install tair
|
||||
```
|
||||
|
||||
To import this vectorstore:
|
||||
## Vector Store
|
||||
|
||||
```python
|
||||
from langchain_community.vectorstores import Tair
|
||||
```
|
||||
|
||||
For a more detailed walkthrough of the Tair wrapper, see [this notebook](/docs/integrations/vectorstores/tair)
|
||||
See a [usage example](/docs/integrations/vectorstores/tair).
|
||||
|
||||
@ -1,81 +1,38 @@
|
||||
# TiDB
|
||||
|
||||
> [TiDB Cloud](https://tidbcloud.com/), is a comprehensive Database-as-a-Service (DBaaS) solution, that provides dedicated and serverless options. TiDB Serverless is now integrating a built-in vector search into the MySQL landscape. With this enhancement, you can seamlessly develop AI applications using TiDB Serverless without the need for a new database or additional technical stacks. Be among the first to experience it by joining the waitlist for the private beta at https://tidb.cloud/ai.
|
||||
> [TiDB Cloud](https://tidbcloud.com/), is a comprehensive Database-as-a-Service (DBaaS) solution,
|
||||
> that provides dedicated and serverless options. `TiDB Serverless` is now integrating
|
||||
> a built-in vector search into the MySQL landscape. With this enhancement, you can seamlessly
|
||||
> develop AI applications using `TiDB Serverless` without the need for a new database or additional
|
||||
> technical stacks. Be among the first to experience it by joining the [waitlist for the private beta](https://tidb.cloud/ai).
|
||||
|
||||
As part of our ongoing efforts to empower TiDB users in leveraging AI application development, we provide support for
|
||||
|
||||
- Memory, enabling the storage of chat history messages directly within TiDB;
|
||||
- TiDB Loader streamlining the process of loading data from TiDB using Langchain;
|
||||
- TiDB Vector Store, enabling the use of TiDB Cloud as a vector store, capitalizing on TiDB's robust database infrastructure.
|
||||
## Installation and Setup
|
||||
|
||||
You have to get the connection details for the TiDB database.
|
||||
Visit the [TiDB Cloud](https://tidbcloud.com/) to get the connection details.
|
||||
|
||||
## Memory
|
||||
|
||||
Utilize TiDB Cloud to store chat message history, leveraging the unlimited scalability of TiDB Cloud Serverless. This enables the storage of massive amounts of historical data without the need to maintain message retention windows.
|
||||
|
||||
```python
|
||||
from langchain_community.chat_message_histories import TiDBChatMessageHistory
|
||||
from langchain_community.chat_message_histories import TiDBChatMessageHistory
|
||||
|
||||
history = TiDBChatMessageHistory(
|
||||
connection_string=tidb_connection_string,
|
||||
session_id="code_gen",
|
||||
)
|
||||
|
||||
history.add_user_message("How's our feature going?")
|
||||
history.add_ai_message(
|
||||
"It's going well. We are working on testing now. It will be released in Feb."
|
||||
)
|
||||
```
|
||||
|
||||
Please refer the details [here](/docs/integrations/memory/tidb_chat_message_history).
|
||||
|
||||
## TiDB Loader
|
||||
|
||||
Effortlessly load data from TiDB into other LangChain components using SQL. This simplifies the integration process, allowing for seamless data manipulation and utilization within your AI applications.
|
||||
```bash
|
||||
## Document loader
|
||||
|
||||
```python
|
||||
from langchain_community.document_loaders import TiDBLoader
|
||||
|
||||
# Setup TiDBLoader to retrieve data
|
||||
loader = TiDBLoader(
|
||||
connection_string=tidb_connection_string,
|
||||
query=f"SELECT * FROM {table_name};",
|
||||
page_content_columns=["name", "description"],
|
||||
metadata_columns=["id"],
|
||||
)
|
||||
|
||||
# Load data
|
||||
documents = loader.load()
|
||||
```
|
||||
|
||||
Please refer the details [here](/docs/integrations/document_loaders/tidb).
|
||||
|
||||
## TiDB Vector Store
|
||||
## Vector store
|
||||
|
||||
With TiDB's exceptional database capabilities, easily manage and store billions of vectorized data. This enhances the performance and scalability of AI applications, providing a robust foundation for your vector storage needs.
|
||||
|
||||
```
|
||||
from typing import List, Tuple
|
||||
from langchain.docstore.document import Document
|
||||
```python
|
||||
from langchain_community.vectorstores import TiDBVectorStore
|
||||
from langchain_openai import OpenAIEmbeddings
|
||||
```
|
||||
Please refer the details [here](/docs/integrations/vectorstores/tidb_vector).
|
||||
|
||||
db = TiDBVectorStore.from_texts(
|
||||
embedding=embeddings,
|
||||
texts=['Andrew like eating oranges', 'Alexandra is from England', 'Ketanji Brown Jackson is a judge'],
|
||||
table_name="tidb_vector_langchain",
|
||||
connection_string=tidb_connection_url,
|
||||
distance_strategy="cosine",
|
||||
)
|
||||
|
||||
query = "Can you tell me about Alexandra?"
|
||||
docs_with_score: List[Tuple[Document, float]] = db.similarity_search_with_score(query)
|
||||
for doc, score in docs_with_score:
|
||||
print("-" * 80)
|
||||
print("Score: ", score)
|
||||
print(doc.page_content)
|
||||
print("-" * 80)
|
||||
## Memory
|
||||
|
||||
```python
|
||||
from langchain_community.chat_message_histories import TiDBChatMessageHistory
|
||||
```
|
||||
|
||||
Please refer the details [here](/docs/integrations/vectorstores/tidb_vector).
|
||||
Please refer the details [here](/docs/integrations/memory/tidb_chat_message_history).
|
||||
|
||||
Loading…
Reference in New Issue