feat(ChatKnowledge):add similarity score and query rewrite

.env.template

@@ -78,6 +78,8 @@ KNOWLEDGE_SEARCH_TOP_SIZE=5
 #KNOWLEDGE_CHUNK_OVERLAP=50
 # Control whether to display the source document of knowledge on the front end.
 KNOWLEDGE_CHAT_SHOW_RELATIONS=False
+# Whether to enable Chat Knowledge Search Rewrite Mode
+KNOWLEDGE_SEARCH_REWRITE=False
 ## EMBEDDING_TOKENIZER   - Tokenizer to use for chunking large inputs
 ## EMBEDDING_TOKEN_LIMIT - Chunk size limit for large inputs
 # EMBEDDING_MODEL=all-MiniLM-L6-v2
@@ -92,16 +94,15 @@ KNOWLEDGE_CHAT_SHOW_RELATIONS=False
 
 
 #*******************************************************************#
-#**                  DATABASE SETTINGS                            **#
+#**                  DB-GPT METADATA DATABASE SETTINGS            **#
 #*******************************************************************#
 ### SQLite database (Current default database)
-LOCAL_DB_PATH=data/default_sqlite.db
 LOCAL_DB_TYPE=sqlite
 
 ### MYSQL database
 # LOCAL_DB_TYPE=mysql
 # LOCAL_DB_USER=root
-# LOCAL_DB_PASSWORD=aa12345678
+# LOCAL_DB_PASSWORD={your_password}
 # LOCAL_DB_HOST=127.0.0.1
 # LOCAL_DB_PORT=3306
 # LOCAL_DB_NAME=dbgpt

docker/examples/metadata/duckdb2mysql.py

@@ -0,0 +1,54 @@
+import duckdb
+import pymysql
+
+""" migrate duckdb to mysql"""
+
+mysql_config = {
+    "host": "127.0.0.1",
+    "user": "root",
+    "password": "your_password",
+    "db": "dbgpt",
+    "charset": "utf8mb4",
+    "cursorclass": pymysql.cursors.DictCursor,
+}
+
+duckdb_files_to_tables = {
+    "pilot/message/chat_history.db": "chat_history",
+    "pilot/message/connect_config.db": "connect_config",
+}
+
+conn_mysql = pymysql.connect(**mysql_config)
+
+
+def migrate_table(duckdb_file_path, source_table, destination_table, conn_mysql):
+    conn_duckdb = duckdb.connect(duckdb_file_path)
+    try:
+        cursor = conn_duckdb.cursor()
+        cursor.execute(f"SELECT * FROM {source_table}")
+        column_names = [
+            desc[0] for desc in cursor.description if desc[0].lower() != "id"
+        ]
+        select_columns = ", ".join(column_names)
+
+        cursor.execute(f"SELECT {select_columns} FROM {source_table}")
+        results = cursor.fetchall()
+
+        with conn_mysql.cursor() as cursor_mysql:
+            for row in results:
+                placeholders = ", ".join(["%s"] * len(row))
+                insert_query = f"INSERT INTO {destination_table} ({', '.join(column_names)}) VALUES ({placeholders})"
+                cursor_mysql.execute(insert_query, row)
+        conn_mysql.commit()
+    finally:
+        conn_duckdb.close()
+
+
+try:
+    for duckdb_file, table in duckdb_files_to_tables.items():
+        print(f"Migrating table {table} from {duckdb_file}...")
+        migrate_table(duckdb_file, table, table, conn_mysql)
+        print(f"Table {table} migrated successfully.")
+finally:
+    conn_mysql.close()
+
+print("Migration completed.")

docker/examples/metadata/duckdb2sqlite.py

@@ -0,0 +1,48 @@
+import duckdb
+import sqlite3
+
+""" migrate duckdb to sqlite"""
+
+duckdb_files_to_tables = {
+    "pilot/message/chat_history.db": "chat_history",
+    "pilot/message/connect_config.db": "connect_config",
+}
+
+sqlite_db_path = "pilot/meta_data/dbgpt.db"
+
+conn_sqlite = sqlite3.connect(sqlite_db_path)
+
+
+def migrate_table(duckdb_file_path, source_table, destination_table, conn_sqlite):
+    conn_duckdb = duckdb.connect(duckdb_file_path)
+    try:
+        cursor_duckdb = conn_duckdb.cursor()
+        cursor_duckdb.execute(f"SELECT * FROM {source_table}")
+        column_names = [
+            desc[0] for desc in cursor_duckdb.description if desc[0].lower() != "id"
+        ]
+        select_columns = ", ".join(column_names)
+
+        cursor_duckdb.execute(f"SELECT {select_columns} FROM {source_table}")
+        results = cursor_duckdb.fetchall()
+
+        cursor_sqlite = conn_sqlite.cursor()
+        for row in results:
+            placeholders = ", ".join(["?"] * len(row))
+            insert_query = f"INSERT INTO {destination_table} ({', '.join(column_names)}) VALUES ({placeholders})"
+            cursor_sqlite.execute(insert_query, row)
+        conn_sqlite.commit()
+        cursor_sqlite.close()
+    finally:
+        conn_duckdb.close()
+
+
+try:
+    for duckdb_file, table in duckdb_files_to_tables.items():
+        print(f"Migrating table {table} from {duckdb_file} to SQLite...")
+        migrate_table(duckdb_file, table, table, conn_sqlite)
+        print(f"Table {table} migrated to SQLite successfully.")
+finally:
+    conn_sqlite.close()
+
+print("Migration to SQLite completed.")

docs/docs/application/advanced_tutorial/rag.md

@@ -1 +1,111 @@
-# RAG Parameter Adjustment
+# RAG Parameter Adjustment
+Each knowledge space supports argument customization, including the relevant arguments for vector retrieval and the arguments for knowledge question-answering prompts.
+
+As shown in the figure below, clicking on the "Knowledge" will trigger a pop-up dialog box. Click the "Arguments" button to enter the parameter tuning interface.
+![image](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/f02039ea-01d7-493a-acd9-027020d54267)
+
+
+<Tabs
+  defaultValue="Embedding"
+  values={[
+    {label: 'Embedding Argument', value: 'Embedding'},
+    {label: 'Prompt Argument', value: 'Prompt'},
+    {label: 'Summary Argument', value: 'Summary'},
+  ]}>
+  <TabItem value="Embedding" label="Embedding Argument">
+
+![image](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/8a69aba0-3b28-449d-8fd8-ce5bf8dbf7fc)
+
+:::tip Embedding Arguments
+* topk:the top k vectors based on similarity score.
+* recall_score:set a similarity threshold score for the retrieval of similar vectors. between 0 and 1. default 0.3.
+* recall_type:recall type. now nly support topk by vector similarity.
+* model:A model used to create vector representations of text or other data.
+* chunk_size:The size of the data chunks used in processing.default 500.
+* chunk_overlap:The amount of overlap between adjacent data chunks.default 50.
+:::
+ </TabItem>
+
+<TabItem value="Prompt" label="Prompt Argument">
+
+![image](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/00f12903-8d70-4bfb-9f58-26f03a6a4773)
+
+:::tip Prompt Arguments
+* scene:A contextual parameter used to define the setting or environment in which the prompt is being used.
+* template:A pre-defined structure or format for the prompt, which can help ensure that the AI system generates responses that are consistent with the desired style or tone.
+* max_token:The maximum number of tokens or words allowed in a prompt. 
+:::
+
+ </TabItem>
+
+<TabItem value="Summary" label="Summary Argument">
+
+![image](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/96782ba2-e9a2-4173-a003-49d44bf874cc)
+
+:::tip summary arguments
+* max_iteration: summary max iteration call with llm, default 5. the bigger and better for document summary but time will cost longer.
+* concurrency_limit: default summary concurrency call with llm, default 3.
+:::
+
+ </TabItem>
+
+</Tabs>
+
+# Knowledge Query Rewrite
+set ``KNOWLEDGE_SEARCH_REWRITE=True`` in ``.env`` file, and restart the server.
+
+```shell
+# Whether to enable Chat Knowledge Search Rewrite Mode
+KNOWLEDGE_SEARCH_REWRITE=True
+```
+
+# Change Vector Database
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+<Tabs
+  defaultValue="Chroma"
+  values={[
+    {label: 'Chroma', value: 'Chroma'},
+    {label: 'Milvus', value: 'Milvus'},
+    {label: 'Weaviate', value: 'Weaviate'},
+  ]}>
+  <TabItem value="Chroma" label="Chroma">
+
+set ``VECTOR_STORE_TYPE`` in ``.env`` file.
+
+```shell
+### Chroma vector db config
+VECTOR_STORE_TYPE=Chroma
+#CHROMA_PERSIST_PATH=/root/DB-GPT/pilot/data
+```
+ </TabItem>
+
+<TabItem value="Milvus" label="Milvus">
+
+
+set ``VECTOR_STORE_TYPE`` in ``.env`` file
+
+```shell
+### Milvus vector db config
+VECTOR_STORE_TYPE=Milvus
+MILVUS_URL=127.0.0.1
+MILVUS_PORT=19530
+#MILVUS_USERNAME
+#MILVUS_PASSWORD
+#MILVUS_SECURE=
+  ```
+ </TabItem>
+
+<TabItem value="Weaviate" label="Weaviate">
+
+set ``VECTOR_STORE_TYPE`` in ``.env`` file
+
+```shell
+### Weaviate vector db config
+VECTOR_STORE_TYPE=Weaviate
+#WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
+ ```
+
+ </TabItem>
+</Tabs>

docs/docs/faq/chatdata.md

@@ -0,0 +1,55 @@
+ChatData & ChatDB
+==================================
+ChatData generates SQL from natural language and executes it. ChatDB involves conversing with metadata from the
+Database, including metadata about databases, tables, and
+fields.![db plugins demonstration](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/d8bfeee9-e982-465e-a2b8-1164b673847e)
+
+### 1.Choose Datasource
+
+If you are using DB-GPT for the first time, you need to add a data source and set the relevant connection information
+for the data source.
+
+```{tip}
+there are some example data in DB-GPT-NEW/DB-GPT/docker/examples
+
+you can execute sql script to generate data.
+```
+
+#### 1.1 Datasource management
+
+![db plugins demonstration](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/7678f07e-9eee-40a9-b980-5b3978a0ed52)
+
+#### 1.2 Connection management
+
+![db plugins demonstration](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/25b8f5a9-d322-459e-a8b2-bfe8cb42bdd6)
+
+#### 1.3 Add Datasource
+
+![db plugins demonstration](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/19ce31a7-4061-4da8-a9cb-efca396cc085)
+
+```{note}
+now DB-GPT support Datasource Type
+
+* Mysql
+* Sqlite
+* DuckDB
+* Clickhouse
+* Mssql
+```
+
+### 2.ChatData
+##### Preview Mode
+After successfully setting up the data source, you can start conversing with the database. You can ask it to generate
+SQL for you or inquire about relevant information on the database's metadata.
+![db plugins demonstration](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/8acf6a42-e511-48ff-aabf-3d9037485c1c)
+
+##### Editor Mode
+In Editor Mode, you can edit your sql and execute it.
+![db plugins demonstration](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/1a896dc1-7c0e-4354-8629-30357ffd8d7f)
+
+
+### 3.ChatDB
+
+![db plugins demonstration](https://github.com/eosphoros-ai/DB-GPT/assets/13723926/e04bc1b1-2c58-4b33-af62-97e89098ace7)
+
+

docs/docs/faq/install.md

@@ -0,0 +1,73 @@
+Installation FAQ
+==================================
+
+
+##### Q1: sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) unable to open database file 
+
+make sure you pull latest code or create directory with mkdir pilot/data
+
+##### Q2: The model keeps getting killed.
+
+your GPU VRAM size is not enough, try replace your hardware or replace other llms.
+
+##### Q3: How to access website on the public network
+
+You can try to use gradio's [network](https://github.com/gradio-app/gradio/blob/main/gradio/networking.py) to achieve.
+```python
+import secrets
+from gradio import networking
+token=secrets.token_urlsafe(32)
+local_port=5000
+url = networking.setup_tunnel('0.0.0.0', local_port, token)
+print(f'Public url: {url}')
+time.sleep(60 * 60 * 24)
+```
+
+Open `url` with your browser to see the website.
+
+##### Q4: (Windows) execute `pip install -e .` error
+
+The error log like the following:
+``` 
+× python setup.py bdist_wheel did not run successfully.
+  │ exit code: 1
+  ╰─> [11 lines of output]
+      running bdist_wheel
+      running build
+      running build_py
+      creating build
+      creating build\lib.win-amd64-cpython-310
+      creating build\lib.win-amd64-cpython-310\cchardet
+      copying src\cchardet\version.py -> build\lib.win-amd64-cpython-310\cchardet
+      copying src\cchardet\__init__.py -> build\lib.win-amd64-cpython-310\cchardet
+      running build_ext
+      building 'cchardet._cchardet' extension
+      error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/
+      [end of output]
+```
+
+Download and install `Microsoft C++ Build Tools` from [visual-cpp-build-tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/)
+
+
+
+##### Q5: `Torch not compiled with CUDA enabled`
+
+```
+2023-08-19 16:24:30 | ERROR | stderr |     raise AssertionError("Torch not compiled with CUDA enabled")
+2023-08-19 16:24:30 | ERROR | stderr | AssertionError: Torch not compiled with CUDA enabled
+```
+
+1. Install [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit-archive)
+2. Reinstall PyTorch [start-locally](https://pytorch.org/get-started/locally/#start-locally) with CUDA support.
+
+
+##### Q6: `How to migrate meta table chat_history and connect_config from duckdb to sqlite`
+```commandline
+ python docker/examples/metadata/duckdb2sqlite.py
+```
+
+##### Q7: `How to migrate meta table chat_history and connect_config from duckdb to mysql`
+```commandline
+1. update your mysql username and password in docker/examples/metadata/duckdb2mysql.py
+2.  python docker/examples/metadata/duckdb2mysql.py
+```