欧美日韩国产免费一区二区三区,,欧美人成片免费看视频,欧美日韩欧美

關(guān)于RAG的定義：

RAG is an AI Framework that integrates large language models (LLMs) with external knowledge retrieval to enhance accuracy and transparency.
Pre-trained language models generate text based on patterns in their training data.
RAG supplements their capabilities by retrieving relevant facts from constantly updated knowledge bases

我們看到了RAG定義中的幾個(gè)關(guān)鍵詞：AI 框架，整合外部知識(shí)，支持即時(shí)更新的知識(shí)庫。

我們看到圖中的 Original/New Connect 類似于我們的外部數(shù)據(jù)（像我們?nèi)粘懙牟┛?，筆記，郵件，電子書什么的），向量數(shù)據(jù)庫Vector database 類似于存儲(chǔ)我們外部知識(shí)的數(shù)據(jù)庫：
市面上常見的向量數(shù)據(jù)庫有很多種：對(duì)于DBA比較熟悉的mongo,es,pg 等等都對(duì)向量數(shù)據(jù)庫有支持，圖中的LLM就是我們之前搭建的大模型，最后我們可以看到Framework 在這架構(gòu)圖中
站在了C位，起到了整合RAG架構(gòu)的核心地位。

關(guān)于Framework 我們選擇 langchain，關(guān)于langchain的定義：

LangChain is a framework for developing applications powered by large language models (LLMs).
LangChain simplifies every stage of the LLM application lifecycle:

Development: Build your applications using LangChain’s open-source building blocks and components. Hit the ground running using third-party integrations and Templates.
Productionization: Use LangSmith to inspect, monitor and evaluate your chains, so that you can continuously optimize and deploy with confidence.
Deployment: Turn any chain into an API with LangServe.

簡單地說就是大模型的一個(gè)開發(fā)框架，支持開發(fā)，持續(xù)優(yōu)化，部署發(fā)布API等功能。

關(guān)于 langchain 對(duì)于 pgvector 的支持: https://python.langchain.com/v0.1/docs/integrations/vectorstores/pgvector/

我們來按照官方的例子運(yùn)行一下demo:

1)安裝LangChain相關(guān)的package

pip3 install langchain_core



pip3 install langchain_postgres



pip3 install psycopg-c



pip3 install langchain-community



pip3 install sentence-transformers

2）我們準(zhǔn)備一下基礎(chǔ)數(shù)據(jù)測試數(shù)據(jù)集：

docs = [



   Document(



       page_content="2024年歐洲杯的冠軍是西班牙隊(duì)",



       metadata={"id": 1, "catalog": "sports", "topic": "CCTV-足球體育新聞"},



   ),



   Document(



       page_content="2023-2024年NBA的總冠軍是波士頓凱爾特人隊(duì)",



       metadata={"id": 2, "catalog": "sports", "topic": "CNN-籃球體育新聞"},



   ),



   Document(



       page_content="2024年9月份postgres會(huì)發(fā)布version17版本,含有大量新的功能",



       metadata={"id": 3, "catalog": "tech", "topic": "開源數(shù)據(jù)庫社區(qū)"},



   ),



   Document(



       page_content="2024年ORACLE發(fā)布了跨時(shí)代意義的數(shù)據(jù)庫版本ORACLE 23AI,支持多模數(shù)據(jù)庫,支持向量數(shù)據(jù)庫",



       metadata={"id": 4, "catalog": "tech", "topic": "甲骨文頻道"},



   ),



]

3）測試程序load 數(shù)據(jù)：

from langchain_core.documents import Document



from langchain_postgres import PGVector



from langchain_huggingface import HuggingFaceEmbeddings



from langchain_postgres.vectorstores import PGVector



# See docker command above to launch a postgres instance with pgvector enabled.



connection = "postgresql+psycopg://app_vector:app_vector@xx.xx.xxx.xxx:5432/postgres"  # Uses psycopg3!



collection_name = "t_news"



embeddings = HuggingFaceEmbeddings(model_name='D:\\AI\\text2vec-base-chinese')



vectorstore = PGVector(



   embeddings=embeddings,



   collection_name="t_news",



   connection=connection,



   use_jsonb=True,



)



docs = [



...



]



print(vectorstore)



##vectorstore.(docs, ids=[doc.metadata["id"] for doc in docs])



vectorstore.add_documents(docs, ids=[doc.metadata["id"] for doc in docs])

4)測試相似度檢索：2024年歐洲杯冠軍，請(qǐng)介紹一下？

vectorstore.similarity_search("2024年歐洲杯冠軍，請(qǐng)介紹一下?", k=1)

我們可以看到embedding 模型給了我們正確的答案。

5）整合大模型接口調(diào)用：

首先我們只是單純的直接調(diào)用大模型接口，感覺他是在胡天?。?！

“歐洲杯的冠軍是葡萄牙隊(duì)，他們?cè)?021年在荷蘭舉行的比賽中擊敗了法國隊(duì)獲得了冠軍。“

葡萄牙應(yīng)該是2016年拿的歐洲杯冠軍??！對(duì)手到是法國隊(duì)。

def LLM(text):



   url = "http://127.0.0.1:8868/llm_query/{}".format(text)  # FastAPI應(yīng)用程序運(yùn)行的地址和端口



   response = requests.get(url)



   print(response.json())



   return response.json()



##def embedding(text):



LLM("2024年歐洲杯冠軍，請(qǐng)介紹一下?")

我們通過RAG增強(qiáng)式檢索：

def LLM(text):



   url = "http://127.0.0.1:8868/llm_query/{}".format(text)  # FastAPI應(yīng)用程序運(yùn)行的地址和端口



   response = requests.get(url)



  # print(response.json())



   return response.json()



def embedding(text):



   return vectorstore.similarity_search(text, k=1)[0].page_content



def RAG(text):



   msg = embedding(text)



   print(msg)



   return LLM(""""{},問題是:{}""".format(msg,text))



if "__main__" ==__name__:



   print(RAG("2024年歐洲杯冠軍，請(qǐng)介紹一下這個(gè)國家？例如這個(gè)國家人口,面積，氣候"))

大模型給我們的答案：相對(duì)于合理的回答

最后我們看一下 langchain 與 pg_vector 的自動(dòng)整合下的數(shù)據(jù)庫表的呈現(xiàn)：
我們發(fā)現(xiàn)langchain 框架會(huì)自動(dòng)創(chuàng)建2張表 langchain_pg_collection和langchain_pg_embedding,

postgres=> \dt



                    List of relations



  Schema   |          Name           | Type  |   Owner    



------------+-------------------------+-------+------------



app_vector | langchain_pg_collection | table | app_vector



app_vector | langchain_pg_embedding  | table | app_vector



(5 rows)



postgres=> \d+ langchain_pg_collection



                                     Table "app_vector.langchain_pg_collection"



 Column   |       Type        | Collation | Nullable | Default | Storage  | Compression | Stats target | Description



-----------+-------------------+-----------+----------+---------+----------+-------------+--------------+-------------



uuid      | uuid              |           | not null |         | plain    |             |              |



name      | character varying |           | not null |         | extended |             |              |



cmetadata | json              |           |          |         | extended |             |              |



Indexes:



   "langchain_pg_collection_pkey" PRIMARY KEY, btree (uuid)



   "langchain_pg_collection_name_key" UNIQUE CONSTRAINT, btree (name)



Referenced by:



   TABLE "langchain_pg_embedding" CONSTRAINT "langchain_pg_embedding_collection_id_fkey" FOREIGN KEY (collection_id) REFERENCES langchain_pg_collection(uuid) ON DELETE CASCADE



Access method: heap



postgres=> \d+ langchain_pg_embedding



                                       Table "app_vector.langchain_pg_embedding"



   Column     |       Type        | Collation | Nullable | Default | Storage  | Compression | Stats target | Description



---------------+-------------------+-----------+----------+---------+----------+-------------+--------------+-------------



id            | character varying |           | not null |         | extended |             |              |



collection_id | uuid              |           |          |         | plain    |             |              |



embedding     | vector            |           |          |         | external |             |              |



document      | character varying |           |          |         | extended |             |              |



cmetadata     | jsonb             |           |          |         | extended |             |              |



Indexes:



   "langchain_pg_embedding_pkey" PRIMARY KEY, btree (id)



   "ix_cmetadata_gin" gin (cmetadata jsonb_path_ops)



   "ix_langchain_pg_embedding_id" UNIQUE, btree (id)



Foreign-key constraints:



   "langchain_pg_embedding_collection_id_fkey" FOREIGN KEY (collection_id) REFERENCES langchain_pg_collection(uuid) ON DELETE CASCADE



Access method: heap

langchain_pg_collection 是主表記錄了向量表的名字：

postgres=> select * from langchain_pg_collection;



                uuid                 |  name  | cmetadata



--------------------------------------+--------+-----------



17e8df97-5db8-442f-8f49-ea6e71231802 | t_news | null



(1 row)

langchain_pg_embedding是子表記錄了向量的信息：

postgres=> select count(1) from langchain_pg_embedding;



count



-------



    4



(1 row)



postgres=> select * from langchain_pg_embedding;



id |            collection_id             |



1  | 17e8df97-5db8-442f-8f49-ea6e71231802 | [-1.3334022,0.9337577,-0.3636402,-0.053306933,0.0846217,-0.08087579,0.7735808,-0.06978625,-0.14796568,0.54863155,0.7147292,0.6



444973,-0.4289818,-0.64992523,-2.0558815,-0.09939844,0.06320713,1.2094835,0.42997867,-0.045221683,-0.74566567,0.9688923,-0.32088393,0.5072144,-0.2132386,-0.38068974,-0.063



253194,-0.5553703,-0.13070923,0.032516792,0.19199787,-0.35632166,-1.0873616,-0.1506536,0.058472667,1.0499889,-0.08423612,-0.17433228,0.771671,-0.48466313,0.57933533,2.0371



673,0.35173145,0.81162024,-0.39255375,0.90436745,0.009064911,0.2791657,-1.1032667,0.8461039,-0.78653026,0.8507371,-0.64681536,0.95859784,0.6849843,0.53893226,0.77747756,0.



0801601,0.17333724,-0.37513876,-1.2156097,0.27867568,-0.92160845,-0.5047081,0.432022,-0.13728906,-0.24497142,-0.5689873,-0.1558505,-1.9338208,-0.35952917,-0.24267699,0.268



40404,-0.17570858,1.3977934,0.3286393,0.47039926,-0.5733993,0.58036995,-0.6639077,0.19822633,-1.0455183,0.115738526,-0.49547425,-0.7333636,-0.61310935,0.3633987,0.1452295,

這里需要注意：默認(rèn)langchain 自動(dòng)生成的表的vector column列并沒有索引，我們可以手動(dòng)創(chuàng)建一下hnsw類型的索引:

postgres=> CREATE INDEX ON langchain_pg_embedding USING hnsw (embedding vector_cosine_ops);



ERROR:  column does not have dimensions

這個(gè)索引錯(cuò)誤是因?yàn)槟阍诔跏蓟蛄康倪^程中沒有指定向量的長度導(dǎo)致的
由于初始化函數(shù)中沒有指定 vector 的長度，導(dǎo)致生成的表也是沒有長度限制的

生成的表：langchain_pg_embedding

postgres=> \d+ langchain_pg_embedding



                                        Table "app_vector.langchain_pg_embedding"



    Column     |       Type        | Collation | Nullable | Default | Storage  | Compression | Stats target | Description



---------------+-------------------+-----------+----------+---------+----------+-------------+--------------+-------------



id            | character varying |           | not null |         | extended |             |              |



collection_id | uuid              |           |          |         | plain    |             |              |



embedding     | vector            |           |          |         | external |             |              |



document      | character varying |           |          |         | extended |             |              |



cmetadata     | jsonb             |           |          |         | extended |             |

查看langchain 代碼：構(gòu)造函數(shù)中是支持傳入vector長度的入?yún)ⅲ篹mbedding_length

vectorstore = PGVector(



    embeddings=embeddings,



    collection_name="t_news_2",



    embedding_length =768,



    connection=connection,



    use_jsonb=True,



)

我們運(yùn)行程序重新生成一下表：vectorstore.drop_tables() 是刪除已存在的表

vectorstore.drop_tables()



vectorstore.add_documents(docs, ids=[doc.metadata["id"] for doc in docs])

再次驗(yàn)證vector的長度：

這回索引可以成功創(chuàng)建了：

postgres=> CREATE INDEX ON langchain_pg_embedding USING hnsw (embedding vector_cosine_ops);



CREATE INDEX

查看langchain 自動(dòng)生成SQL的執(zhí)行計(jì)劃：我們看到了觸發(fā)了我們之前創(chuàng)建的索引Index Scan using langchain_pg_embedding_embedding_idx on langchain_pg_embedding

explain analyze SELECT langchain_pg_embedding.id AS langchain_pg_embedding_id, langchain_pg_embedding.collection_id AS langchain_pg_embedding_collection_id,



langchain_pg_embedding.embedding AS langchain_pg_embedding_embedding, langchain_pg_embedding.document AS langchain_pg_embedding_document,



langchain_pg_embedding.cmetadata AS langchain_pg_embedding_cmetadata, langchain_pg_embedding.embedding <=>



'[-0.77009904,1.1517035,...]'



AS distance



    FROM langchain_pg_embedding JOIN langchain_pg_collection ON langchain_pg_embedding.collection_id = langchain_pg_collection.uuid



    WHERE langchain_pg_embedding.collection_id = 'a9112e1a-ec73-4742-9d88-806c09c525b4' ORDER BY distance ASC



     LIMIT 1;



Limit  (cost=12.18..24.26 rows=1 width=152) (actual time=0.164..0.165 rows=1 loops=1)



   ->  Nested Loop  (cost=12.18..24.26 rows=1 width=152) (actual time=0.164..0.164 rows=1 loops=1)



         ->  Index Scan using langchain_pg_embedding_embedding_idx on langchain_pg_embedding  (cost=12.03..16.08 rows=1 width=144) (actual time=0.148..0.149 rows=1 loops=1



)



               Order By: (embedding <=> '[-0.77009904,1.1517035,-0.14216383,-0.7595568,...]'::vector)



               Filter: (collection_id = 'a9112e1a-ec73-4742-9d88-806c09c525b4'::uuid)



         ->  Index Only Scan using langchain_pg_collection_pkey on langchain_pg_collection  (cost=0.15..8.17 rows=1 width=16) (actual time=0.005..0.005 rows=1 loops=1)



               Index Cond: (uuid = 'a9112e1a-ec73-4742-9d88-806c09c525b4'::uuid)



               Heap Fetches: 1



Planning Time: 0.116 ms



Execution Time: 0.622 ms



(10 rows)

最后我們總結(jié)一下：

1.Langchain 是一個(gè)整合AI大模型調(diào)用和本地embedding 向量寫入整合的一個(gè)AI開發(fā)框架，可以幫我們快速實(shí)現(xiàn)RAG的開發(fā)
2.langchain 和 pgvector 整合的時(shí)候，需要注意初始化pgvector 對(duì)象的時(shí)候，要制定embedding 的長度，否則自動(dòng)創(chuàng)建的表vector是沒有長度限制的，
導(dǎo)致不能創(chuàng)建索引的錯(cuò)誤：ERROR: column does not have dimensions

本文章轉(zhuǎn)載微信公眾號(hào)@PostgreSQL知識(shí)庫