git piMerge branch 'main' into dev

Author: eric-epsilla

.github/workflows/pypi-publish.yml

@@ -11,7 +11,7 @@ name: Upload Python Package
 on:
   push:
     branches: [ "main" ]
-    paths: ['pyepsilla/vectordb/version.py']
+    paths: ['pyepsilla/vectordb/version.py', 'pyproject.toml']
 
 jobs:
   deploy:

README.md

@@ -25,22 +25,30 @@ docker pull epsilla/vectordb
 docker run -d -p 8888:8888 epsilla/vectordb
 ```
 
+#### When Port 8888 conflicted with Jupyter Notebook
+If you are using Jupyter Notebook on localhost, the port 8888 maybe conflict!
+
+So you can change the vectordb port to another number, such as 18888
+```
+docker run -d -p 18888:8888 epsilla/vectordb
+```
+
 #### Use pyepsilla to connect to and interact with local vector database
 
 ```python
 from pyepsilla import vectordb
 
-## connect to vectordb
+## 1.Connect to vectordb
 client = vectordb.Client(
   host='localhost',
   port='8888'
 )
 
-## load and use a database
+## 2.Load and use a database
 client.load_db(db_name="MyDB", db_path="/tmp/epsilla")
 client.use_db(db_name="MyDB")
 
-## create a table in the current database
+## 3.Create a table in the current database
 client.create_table(
   table_name="MyTable",
   table_fields=[
@@ -50,7 +58,7 @@ client.create_table(
   ]
 )
 
-## insert records
+## 4.Insert records
 client.insert(
   table_name="MyTable",
   records=[
@@ -62,7 +70,7 @@ client.insert(
   ]
 )
 
-## search with specific response field
+## 5.Search with specific response field
 status_code, response = client.query(
   table_name="MyTable",
   query_field="Embedding",
@@ -72,7 +80,7 @@ status_code, response = client.query(
 )
 print(response)
 
-## search without specific response field, then it will return all fields
+## 6.Search without specific response field, then it will return all fields
 status_code, response = client.query(
   table_name="MyTable",
   query_field="Embedding",
@@ -81,16 +89,16 @@ status_code, response = client.query(
 )
 print(response)
 
-## delete records by primary_keys (and filter)
+## 7.Delete records by primary_keys (and filter)
 status_code, response =  client.delete(table_name="MyTable", primary_keys=[3, 4])
 status_code, response =  client.delete(table_name="MyTable", filter="Doc <> 'San Francisco'")
 print(response)
 
 
-## drop a table
+## 8.Drop a table
 client.drop_table("MyTable")
 
-## unload a database from memory
+## 9.Unload a database from memory
 client.unload_db("MyDB")
 ```
 
@@ -101,34 +109,86 @@ client.unload_db("MyDB")
 https://cloud.epsilla.com
 
 #### Use Epsilla Cloud module to connect with the vectordb
-Please check <a href="https://github.com/epsilla-cloud/epsilla-python-client/blob/main/examples/hello_epsilla_cloud.py">example</a> for detail.
+Please get the project_id, db_id, epsilla_api_key from Epsilla Cloud at first
 ```python3
 from pyepsilla import cloud
 
-# Connect to Epsilla Cloud
-client = cloud.Client(project_id="32ef3a3f-****-****-****-************", api_key="eps_**********")
+epsilla_api_key = os.getenv("EPSILLA_API_KEY", "Your-Epsilla-API-Key")
+project_id = os.getenv("EPSILLA_PROJECT_ID", "Your-Project-ID")
+db_id = os.getenv("EPSILLA_DB_ID", "Your-DB-ID")
+
+
+# 1.Connect to Epsilla Cloud
+client = cloud.Client(project_id="*****-****-****-****-************", api_key="eps_**********")
+
+# 2.Connect to Vectordb
+db_client = cloud_client.vectordb(db_id)
+
+# 3.Create a table with schema
+status_code, response = db.create_table(
+    table_name="MyTable",
+    table_fields=[
+        {"name": "ID", "dataType": "INT", "primaryKey": True},
+        {"name": "Doc", "dataType": "STRING"},
+        {"name": "Embedding", "dataType": "VECTOR_FLOAT", "dimensions": 4},
+    ],
+)
+print(status_code, response)
+
+# 4.Insert new vector records into table
+status_code, response = db.insert(
+    table_name="MyTable",
+    records=[
+        {"ID": 1, "Doc": "Berlin", "Embedding": [0.05, 0.61, 0.76, 0.74]},
+        {"ID": 2, "Doc": "London", "Embedding": [0.19, 0.81, 0.75, 0.11]},
+        {"ID": 3, "Doc": "Moscow", "Embedding": [0.36, 0.55, 0.47, 0.94]},
+        {"ID": 4, "Doc": "San Francisco", "Embedding": [0.18, 0.01, 0.85, 0.80]},
+        {"ID": 5, "Doc": "Shanghai", "Embedding": [0.24, 0.18, 0.22, 0.44]},
+    ],
+)
+print(status_code, response)
+
+
+# 5.Query Vectors with specific response field, otherwise it will return all fields
+status_code, response = db.query(
+    table_name="MyTable",
+    query_field="Embedding",
+    query_vector=[0.35, 0.55, 0.47, 0.94],
+    response_fields=["Doc"],
+    limit=2,
+)
+print(status_code, response)
+
+
+# 6.Delete specific records from table
+status_code, response = db.delete(table_name="MyTable", primary_keys=[4, 5])
+status_code, response = db.delete(table_name="MyTable", filter="Doc <> 'San Francisco'")
+print(status_code, response)
+
+# 7.Drop table
+status_code, response = db.drop_table(table_name="MyTable")
+print(status_code, response)
+
 
-# Connect to Vectordb
-db = client.vectordb(db_id="df7431d0-****-****-****-************")
 ```
 
 
 ## Connect to Epsilla RAG
-
+Please get the project_id, epsilla_api_key, ragapp_id, converstation_id(optional) from Epsilla Cloud at first
 The resp will contains answer as well as contexts, like {"answer": "****", "contexts": ['context1','context2', ...]}
 
 ```python3
 from pyepsilla import cloud
 
-# Connect to Epsilla RAG
+# 1.Connect to Epsilla RAG
 client = cloud.RAG(
     project_id="ce07c6fc-****-****-b7bd-b7819f22bcff",
     api_key="eps_**********",
     ragapp_id="153a5a49-****-****-b2b8-496451eda8b5",
     conversation_id="6fa22a6a-****-****-b1c3-5c795d0f45ef",
 )
 
-# Start a new conversation with RAG
+# 2.Start a new conversation with RAG
 client.start_new_conversation()
 resp = client.query("What's RAG?")
 

pyepsilla/vectordb/readme.md

@@ -1,2 +1 @@
-##https://github.com/hegelai/prompttools/blob/main/examples/notebooks/ChromaDBExperiment.ipynb
-## torch/sentence_transformers/sentence-transformers_paraphrase-MiniLM-L3-v2
+

pyproject.toml

@@ -8,7 +8,7 @@ readme = "README.md"
 [tool.poetry.dependencies]
 python = ">=3.10"
 boto3 = "^1.35.5"
-posthog = "^3.6.0"
+posthog = "^3.6.3"
 py-machineid = "^0.6.0"
 sentry-sdk = "^2.13.0"
 requests = "^2.32.3"