ragflow-cli 0.25.0.dev6__tar.gz → 0.25.2__tar.gz

{ragflow_cli-0.25.0.dev6 → ragflow_cli-0.25.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ragflow-cli
-Version: 0.25.0.dev6
+Version: 0.25.2
 Summary: Admin Service's client of [RAGFlow](https://github.com/infiniflow/ragflow). The Admin Service provides user management and system monitoring. 
 Author-email: Lynn <lynn_inf@hotmail.com>
 License: Apache License, Version 2.0
@@ -62,7 +62,7 @@ It consists of a server-side Service and a command-line client (CLI), both imple
 1.  Ensure the Admin Service is running.
 2.  Install ragflow-cli.
     ```bash
-    pip install ragflow-cli==0.24.0
+    pip install ragflow-cli==0.25.2
     ```
 3.  Launch the CLI client:
     ```bash

{ragflow_cli-0.25.0.dev6 → ragflow_cli-0.25.2}/README.md

@@ -48,7 +48,7 @@ It consists of a server-side Service and a command-line client (CLI), both imple
 1.  Ensure the Admin Service is running.
 2.  Install ragflow-cli.
     ```bash
-    pip install ragflow-cli==0.24.0
+    pip install ragflow-cli==0.25.2
     ```
 3.  Launch the CLI client:
     ```bash

{ragflow_cli-0.25.0.dev6 → ragflow_cli-0.25.2}/parser.py

@@ -77,10 +77,17 @@ sql_command: login_user
            | drop_user_dataset
            | list_user_datasets
            | list_user_dataset_files
+           | list_user_dataset_documents
+           | list_user_datasets_metadata
+           | list_user_documents_metadata_summary
            | list_user_agents
            | list_user_chats
            | create_user_chat
            | drop_user_chat
+           | create_dataset_table
+           | drop_dataset_table
+           | create_metadata_table
+           | drop_metadata_table
            | list_user_model_providers
            | list_user_default_models
            | parse_dataset_docs
@@ -88,6 +95,14 @@ sql_command: login_user
            | parse_dataset_async
            | import_docs_into_dataset
            | search_on_datasets
+           | get_chunk
+           | list_chunks
+           | insert_dataset_from_file
+           | insert_metadata_from_file
+           | update_chunk
+           | set_metadata
+           | remove_tags
+           | remove_chunks
            | create_chat_session
            | drop_chat_session
            | list_chat_sessions
@@ -103,10 +118,12 @@ sql_command: login_user
 // meta command definition
 meta_command: "\\" meta_command_name [meta_args]
 
+COMMA: ","
+
 meta_command_name: /[a-zA-Z?]+/
 meta_args: (meta_arg)+
 
-meta_arg: /[^\\s"']+/ | quoted_string
+meta_arg: /[^\s"',]+/ | quoted_string
 
 // command definition
 
@@ -127,6 +144,7 @@ ALTER: "ALTER"i
 ACTIVE: "ACTIVE"i
 ADMIN: "ADMIN"i
 PASSWORD: "PASSWORD"i
+DATASET_TABLE: "DATASET TABLE"i
 DATASET: "DATASET"i
 DATASETS: "DATASETS"i
 OF: "OF"i
@@ -161,11 +179,18 @@ DEFAULT: "DEFAULT"i
 CHATS: "CHATS"i
 CHAT: "CHAT"i
 FILES: "FILES"i
+DOCUMENT: "DOCUMENT"i
+DOCUMENTS: "DOCUMENTS"i
+METADATA: "METADATA"i
+SUMMARY: "SUMMARY"i
 AS: "AS"i
 PARSE: "PARSE"i
 IMPORT: "IMPORT"i
 INTO: "INTO"i
+IN: "IN"i
 WITH: "WITH"i
+VECTOR: "VECTOR"i
+SIZE: "SIZE"i
 PARSER: "PARSER"i
 PIPELINE: "PIPELINE"i
 SEARCH: "SEARCH"i
@@ -187,8 +212,21 @@ FINGERPRINT: "FINGERPRINT"i
 LICENSE: "LICENSE"i
 CHECK: "CHECK"i
 CONFIG: "CONFIG"i
-
-login_user: LOGIN USER quoted_string ";"
+INDEX: "INDEX"i
+TABLE: "TABLE"i
+CHUNK: "CHUNK"i
+CHUNKS: "CHUNKS"i
+GET: "GET"i
+INSERT: "INSERT"i
+PAGE: "PAGE"i
+KEYWORDS: "KEYWORDS"i
+AVAILABLE: "AVAILABLE"i
+FILE: "FILE"i
+UPDATE: "UPDATE"i
+REMOVE: "REMOVE"i
+TAGS: "TAGS"i
+
+login_user: LOGIN USER quoted_string (PASSWORD quoted_string)? ";"
 list_services: LIST SERVICES ";"
 show_service: SHOW SERVICE NUMBER ";"
 startup_service: STARTUP SERVICE NUMBER ";"
@@ -271,6 +309,9 @@ user_statement: ping_server
                 | list_user_default_models
                 | import_docs_into_dataset
                 | search_on_datasets
+                | update_chunk
+                | set_metadata
+                | remove_tags
                 | create_chat_session
                 | drop_chat_session
                 | list_chat_sessions
@@ -299,6 +340,9 @@ create_user_dataset_with_parser: CREATE DATASET quoted_string WITH EMBEDDING quo
 create_user_dataset_with_pipeline: CREATE DATASET quoted_string WITH EMBEDDING quoted_string PIPELINE quoted_string ";" 
 drop_user_dataset: DROP DATASET quoted_string ";"
 list_user_dataset_files: LIST FILES OF DATASET quoted_string ";"
+list_user_dataset_documents: LIST DOCUMENTS OF DATASET quoted_string ";"
+list_user_datasets_metadata: LIST METADATA OF DATASETS quoted_string (COMMA quoted_string)* ";"
+list_user_documents_metadata_summary: LIST METADATA SUMMARY OF DATASET quoted_string (DOCUMENTS quoted_string (COMMA quoted_string)*)? ";"
 list_user_agents: LIST AGENTS ";"
 list_user_chats: LIST CHATS ";"
 create_user_chat: CREATE CHAT quoted_string ";"
@@ -311,12 +355,27 @@ list_user_model_providers: LIST MODEL PROVIDERS ";"
 list_user_default_models: LIST DEFAULT MODELS ";"
 import_docs_into_dataset: IMPORT quoted_string INTO DATASET quoted_string ";"
 search_on_datasets: SEARCH quoted_string ON DATASETS quoted_string ";"
+get_chunk: GET CHUNK quoted_string ";"
+list_chunks: LIST CHUNKS OF DOCUMENT quoted_string ("PAGE" NUMBER)? ("SIZE" NUMBER)? ("KEYWORDS" quoted_string)? ("AVAILABLE" NUMBER)? ";"
+set_metadata: SET METADATA OF DOCUMENT quoted_string TO quoted_string ";"
+remove_tags: REMOVE TAGS quoted_string (COMMA quoted_string)* FROM DATASET quoted_string ";"
+remove_chunks: REMOVE CHUNKS quoted_string (COMMA quoted_string)* FROM DOCUMENT quoted_string ";"
+           | REMOVE ALL CHUNKS FROM DOCUMENT quoted_string ";"
 
 parse_dataset_docs: PARSE quoted_string OF DATASET quoted_string ";"
 parse_dataset_sync: PARSE DATASET quoted_string SYNC ";"
 parse_dataset_async: PARSE DATASET quoted_string ASYNC ";"
 
-identifier_list: identifier ("," identifier)*
+// Internal CLI only for GO
+create_dataset_table: CREATE DATASET TABLE quoted_string VECTOR SIZE NUMBER ";"
+drop_dataset_table: DROP DATASET TABLE quoted_string ";"
+create_metadata_table: CREATE METADATA TABLE ";"
+drop_metadata_table: DROP METADATA TABLE ";"
+insert_dataset_from_file: INSERT DATASET FROM FILE quoted_string ";"
+insert_metadata_from_file: INSERT METADATA FROM FILE quoted_string ";"
+update_chunk: UPDATE CHUNK quoted_string OF DATASET quoted_string SET quoted_string ";"
+
+identifier_list: identifier (COMMA identifier)*
 
 identifier: WORD
 quoted_string: QUOTED_STRING
@@ -340,7 +399,13 @@ class RAGFlowCLITransformer(Transformer):
 
     def login_user(self, items):
         email = items[2].children[0].strip("'\"")
-        return {"type": "login_user", "email": email}
+        if len(items) == 5:
+            # With password: LOGIN USER email PASSWORD password
+            password = items[4].children[0].strip("'\"")
+            return {"type": "login_user", "email": email, "password": password}
+        else:
+            # Without password: LOGIN USER email
+            return {"type": "login_user", "email": email}
 
     def ping_server(self, items):
         return {"type": "ping_server"}
@@ -592,6 +657,28 @@ class RAGFlowCLITransformer(Transformer):
         dataset_name = items[4].children[0].strip("'\"")
         return {"type": "list_user_dataset_files", "dataset_name": dataset_name}
 
+    def list_user_dataset_documents(self, items):
+        dataset_name = items[4].children[0].strip("'\"")
+        return {"type": "list_user_dataset_documents", "dataset_name": dataset_name}
+
+    def list_user_datasets_metadata(self, items):
+        dataset_names = []
+        dataset_names.append(items[4].children[0].strip("'\""))
+        for i in range(5, len(items)):
+            if items[i] and hasattr(items[i], 'children') and items[i].children:
+                dataset_names.append(items[i].children[0].strip("'\""))
+        return {"type": "list_user_datasets_metadata", "dataset_names": dataset_names}
+
+    def list_user_documents_metadata_summary(self, items):
+        dataset_name = items[5].children[0].strip("'\"")
+        doc_ids = []
+        if len(items) > 6 and items[6] == "DOCUMENTS":
+            for i in range(7, len(items)):
+                if items[i] and hasattr(items[i], 'children') and items[i].children:
+                    doc_id = items[i].children[0].strip("'\"")
+                    doc_ids.append(doc_id)
+        return {"type": "list_user_documents_metadata_summary", "dataset_name": dataset_name, "document_ids": doc_ids}
+
     def list_user_agents(self, items):
         return {"type": "list_user_agents"}
 
@@ -606,6 +693,30 @@ class RAGFlowCLITransformer(Transformer):
         chat_name = items[2].children[0].strip("'\"")
         return {"type": "drop_user_chat", "chat_name": chat_name}
 
+    def create_dataset_table(self, items):
+        dataset_name = None
+        vector_size = None
+        for i, item in enumerate(items):
+            if hasattr(item, 'data') and item.data == 'quoted_string':
+                dataset_name = item.children[0].strip("'\"")
+            if hasattr(item, 'type') and item.type == 'NUMBER':
+                if i > 0 and items[i-1].type == 'SIZE' and items[i-2].type == 'VECTOR':
+                    vector_size = int(item)
+        return {"type": "create_dataset_table", "dataset_name": dataset_name, "vector_size": vector_size}
+
+    def drop_dataset_table(self, items):
+        dataset_name = None
+        for item in items:
+            if hasattr(item, 'data') and item.data == 'quoted_string':
+                dataset_name = item.children[0].strip("'\"")
+        return {"type": "drop_dataset_table", "dataset_name": dataset_name}
+
+    def create_metadata_table(self, items):
+        return {"type": "create_metadata_table"}
+
+    def drop_metadata_table(self, items):
+        return {"type": "drop_metadata_table"}
+
     def list_user_model_providers(self, items):
         return {"type": "list_user_model_providers"}
 
@@ -666,6 +777,103 @@ class RAGFlowCLITransformer(Transformer):
             datasets = datasets.split(" ")
         return {"type": "search_on_datasets", "datasets": datasets, "question": question}
 
+    def get_chunk(self, items):
+        chunk_id = items[2].children[0].strip("'\"")
+        return {"type": "get_chunk", "chunk_id": chunk_id}
+
+    def insert_dataset_from_file(self, items):
+        file_path = items[4].children[0].strip("'\"")
+        return {"type": "insert_dataset_from_file", "file_path": file_path}
+
+    def insert_metadata_from_file(self, items):
+        file_path = items[4].children[0].strip("'\"")
+        return {"type": "insert_metadata_from_file", "file_path": file_path}
+
+    def update_chunk(self, items):
+        def get_quoted_value(item):
+            if hasattr(item, 'children') and item.children:
+                return item.children[0].strip("'\"")
+            return str(item).strip("'\"")
+
+        chunk_id = get_quoted_value(items[2])
+        dataset_name = get_quoted_value(items[5])
+        json_body = get_quoted_value(items[7])
+        return {"type": "update_chunk", "chunk_id": chunk_id, "dataset_name": dataset_name, "json_body": json_body}
+
+    def set_metadata(self, items):
+        doc_id = items[4].children[0].strip("'\"")
+        meta_json = items[6].children[0].strip("'\"")
+        return {"type": "set_metadata", "doc_id": doc_id, "meta": meta_json}
+
+    def remove_tags(self, items):
+        # items: REMOVE, TAGS, quoted_string(tag1), quoted_string(tag2), ..., FROM, DATASET, quoted_string(dataset_name), ";"
+        tags = []
+        # Start from index 2 (after TAGS keyword) and parse quoted strings until FROM
+        for i in range(2, len(items)):
+            item = items[i]
+            # Check for FROM token to stop
+            if hasattr(item, 'type') and item.type == 'FROM':
+                break
+            if hasattr(item, 'children') and item.children:
+                tag = item.children[0].strip("'\"")
+                tags.append(tag)
+        # Find dataset_name: quoted_string after DATASET
+        dataset_name = None
+        for i, item in enumerate(items):
+            # Check if item is a DATASET token
+            if hasattr(item, 'type') and item.type == 'DATASET':
+                # Next item should be quoted_string
+                dataset_name = items[i + 1].children[0].strip("'\"")
+                break
+        return {"type": "remove_tags", "dataset_name": dataset_name, "tags": tags}
+
+    def remove_chunks(self, items):
+        # Handle two cases:
+        # 1. REMOVE CHUNKS quoted_string (COMMA quoted_string)* FROM DOCUMENT quoted_string ";"
+        # 2. REMOVE ALL CHUNKS FROM DOCUMENT quoted_string ";"
+
+        # Check if it's "REMOVE ALL CHUNKS"
+        for item in items:
+            if hasattr(item, 'type') and item.type == 'ALL':
+                # Find doc_id
+                for j, inner_item in enumerate(items):
+                    if hasattr(inner_item, 'type') and inner_item.type == 'DOCUMENT':
+                        doc_id = items[j + 1].children[0].strip("'\"")
+                        return {"type": "remove_chunks", "doc_id": doc_id, "delete_all": True}
+
+        # Otherwise, we have chunk_ids
+        chunk_ids = []
+        doc_id = None
+        for i, item in enumerate(items):
+            if hasattr(item, 'type') and item.type == 'DOCUMENT':
+                doc_id = items[i + 1].children[0].strip("'\"")
+            elif hasattr(item, 'children') and item.children:
+                val = item.children[0].strip("'\"")
+                # Skip if it's "FROM" or "DOCUMENT"
+                if val.upper() in ['FROM', 'DOCUMENT']:
+                    continue
+                chunk_ids.append(val)
+
+        return {"type": "remove_chunks", "doc_id": doc_id, "chunk_ids": chunk_ids}
+
+    def list_chunks(self, items):
+        doc_id = items[4].children[0].strip("'\"")
+        result = {"type": "list_chunks", "doc_id": doc_id}
+
+        # Parse optional parameters: PAGE, SIZE, KEYWORDS, AVAILABLE
+        # items structure varies based on which params are present
+        for i, item in enumerate(items):
+            if str(item) == "PAGE":
+                result["page"] = int(items[i + 1])
+            elif str(item) == "SIZE":
+                result["size"] = int(items[i + 1])
+            elif str(item) == "KEYWORDS":
+                result["keywords"] = items[i + 1].children[0].strip("'\"")
+            elif str(item) == "AVAILABLE":
+                result["available_int"] = int(items[i + 1])
+
+        return result
+
     def benchmark(self, items):
         concurrency: int = int(items[1])
         iterations: int = int(items[2])

{ragflow_cli-0.25.0.dev6 → ragflow_cli-0.25.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ragflow-cli"
-version = "0.25.0.dev6"
+version = "0.25.2"
 description = "Admin Service's client of [RAGFlow](https://github.com/infiniflow/ragflow). The Admin Service provides user management and system monitoring. "
 authors = [{ name = "Lynn", email = "lynn_inf@hotmail.com" }]
 license = { text = "Apache License, Version 2.0" }

{ragflow_cli-0.25.0.dev6 → ragflow_cli-0.25.2}/ragflow_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ragflow-cli
-Version: 0.25.0.dev6
+Version: 0.25.2
 Summary: Admin Service's client of [RAGFlow](https://github.com/infiniflow/ragflow). The Admin Service provides user management and system monitoring. 
 Author-email: Lynn <lynn_inf@hotmail.com>
 License: Apache License, Version 2.0
@@ -62,7 +62,7 @@ It consists of a server-side Service and a command-line client (CLI), both imple
 1.  Ensure the Admin Service is running.
 2.  Install ragflow-cli.
     ```bash
-    pip install ragflow-cli==0.24.0
+    pip install ragflow-cli==0.25.2
     ```
 3.  Launch the CLI client:
     ```bash

{ragflow_cli-0.25.0.dev6 → ragflow_cli-0.25.2}/ragflow_cli.py

@@ -18,6 +18,9 @@ import sys
 import argparse
 import base64
 import getpass
+import os
+import atexit
+import readline
 from cmd import Cmd
 from typing import Any, Dict, List
 
@@ -61,6 +64,12 @@ class RAGFlowCLI(Cmd):
         self.port: int = 0
         self.mode: str = "admin"
         self.ragflow_client = None
+        # History file for readline persistence
+        self.history_file = os.path.expanduser("~/.ragflow_cli_history")
+        # Load existing history
+        self._load_history()
+        # Register cleanup to save history on exit
+        atexit.register(self._save_history)
 
     intro = r"""Type "\h" for help."""
     prompt = "ragflow> "
@@ -99,6 +108,7 @@ class RAGFlowCLI(Cmd):
             return {"type": "empty"}
 
         self.command_history.append(command_str)
+        readline.add_history(command_str)
 
         try:
             result = self.parser.parse(command_str)
@@ -210,6 +220,21 @@ class RAGFlowCLI(Cmd):
 
         print(separator)
 
+    def _load_history(self):
+        """Load command history from file."""
+        try:
+            if os.path.exists(self.history_file):
+                readline.read_history_file(self.history_file)
+        except Exception:
+            pass  # Ignore errors loading history
+
+    def _save_history(self):
+        """Save command history to file."""
+        try:
+            readline.write_history_file(self.history_file)
+        except Exception:
+            pass  # Ignore errors saving history
+
     def run_interactive(self, args):
         if self.verify_auth(args, single_command=False, auth=args["auth"]):
             print(r"""