File size: 19,717 Bytes
979853c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
"""
Utility functions for the LightRAG API.
"""

import os
import argparse
from typing import Optional, List, Tuple
import sys
import time
import logging
from ascii_colors import ASCIIColors
from .._version import __api_version__ as api_version
from .._version import __version__ as core_version
from lightrag.constants import (
    DEFAULT_FORCE_LLM_SUMMARY_ON_MERGE,
)
from lightrag.api.runtime_validation import validate_runtime_target_from_env_file
from fastapi import HTTPException, Security, Request, Response, status
from fastapi.security import APIKeyHeader, OAuth2PasswordBearer
from starlette.status import HTTP_403_FORBIDDEN
from .auth import auth_handler
from .config import ollama_server_infos, global_args, get_env_value

logger = logging.getLogger("lightrag")

# ========== Token Renewal Rate Limiting ==========
# Cache to track last renewal time per user (username as key)
# Format: {username: last_renewal_timestamp}
_token_renewal_cache: dict[str, float] = {}
_RENEWAL_MIN_INTERVAL = 60  # Minimum 60 seconds between renewals for same user

# ========== Token Renewal Path Exclusions ==========
# Paths that should NOT trigger token auto-renewal
# - /health: Health check endpoint, no login required
# - /documents/paginated: Client polls this frequently (5-30s), renewal not needed
# - /documents/pipeline_status: Client polls this very frequently (2s), renewal not needed
_TOKEN_RENEWAL_SKIP_PATHS = [
    "/health",
    "/documents/paginated",
    "/documents/pipeline_status",
]


def check_env_file():
    """
    Check if .env file exists and handle user confirmation if needed.
    Returns True if should continue, False if should exit.
    """
    env_path = ".env"

    if not os.path.exists(env_path):
        warning_msg = "Warning: Startup directory must contain .env file for multi-instance support."
        ASCIIColors.yellow(warning_msg)

        # Check if running in interactive terminal
        if sys.stdin.isatty():
            response = input("Do you want to continue? (yes/NO): ")
            if response.lower() != "yes":
                ASCIIColors.red("Server startup cancelled")
                return False
        return True

    is_valid, error_message = validate_runtime_target_from_env_file(env_path)
    if not is_valid:
        for line in error_message.splitlines():
            ASCIIColors.red(line)
        return False

    return True


# Get whitelist paths from global_args, only once during initialization
whitelist_paths = global_args.whitelist_paths.split(",")

# Pre-compile path matching patterns
whitelist_patterns: List[Tuple[str, bool]] = []
for path in whitelist_paths:
    path = path.strip()
    if path:
        # If path ends with /*, match all paths with that prefix
        if path.endswith("/*"):
            prefix = path[:-2]
            whitelist_patterns.append((prefix, True))  # (prefix, is_prefix_match)
        else:
            whitelist_patterns.append((path, False))  # (exact_path, is_prefix_match)

# Global authentication configuration
auth_configured = bool(auth_handler.accounts)


def get_combined_auth_dependency(api_key: Optional[str] = None):
    """
    Create a combined authentication dependency that implements authentication logic
    based on API key, OAuth2 token, and whitelist paths.

    Args:
        api_key (Optional[str]): API key for validation

    Returns:
        Callable: A dependency function that implements the authentication logic
    """
    # Use global whitelist_patterns and auth_configured variables
    # whitelist_patterns and auth_configured are already initialized at module level

    # Only calculate api_key_configured as it depends on the function parameter
    api_key_configured = bool(api_key)

    # Create security dependencies with proper descriptions for Swagger UI
    oauth2_scheme = OAuth2PasswordBearer(
        tokenUrl="login", auto_error=False, description="OAuth2 Password Authentication"
    )

    # If API key is configured, create an API key header security
    api_key_header = None
    if api_key_configured:
        api_key_header = APIKeyHeader(
            name="X-API-Key", auto_error=False, description="API Key Authentication"
        )

    async def combined_dependency(
        request: Request,
        response: Response,  # Added: needed to return new token via response header
        token: str = Security(oauth2_scheme),
        api_key_header_value: Optional[str] = None
        if api_key_header is None
        else Security(api_key_header),
    ):
        # 1. Check if path is in whitelist
        path = request.url.path
        for pattern, is_prefix in whitelist_patterns:
            if (is_prefix and path.startswith(pattern)) or (
                not is_prefix and path == pattern
            ):
                return  # Whitelist path, allow access

        # 2. Validate token first if provided in the request (Ensure 401 error if token is invalid)
        if token:
            try:
                token_info = auth_handler.validate_token(token)

                # ========== Token Auto-Renewal Logic ==========
                from lightrag.api.config import global_args
                from datetime import datetime, timezone

                if global_args.token_auto_renew:
                    # Check if current path should skip token renewal
                    skip_renewal = any(
                        path == skip_path or path.startswith(skip_path + "/")
                        for skip_path in _TOKEN_RENEWAL_SKIP_PATHS
                    )

                    if skip_renewal:
                        logger.debug(f"Token auto-renewal skipped for path: {path}")
                    else:
                        try:
                            expire_time = token_info.get("exp")
                            if expire_time:
                                # Calculate remaining time ratio
                                now = datetime.now(timezone.utc)
                                remaining_seconds = (expire_time - now).total_seconds()

                                # Get original token expiration duration
                                role = token_info.get("role", "user")
                                total_hours = (
                                    auth_handler.guest_expire_hours
                                    if role == "guest"
                                    else auth_handler.expire_hours
                                )
                                total_seconds = total_hours * 3600

                                # Issue new token if remaining time < threshold
                                if (
                                    remaining_seconds
                                    < total_seconds * global_args.token_renew_threshold
                                ):
                                    # ========== Rate Limiting Check ==========
                                    username = token_info["username"]
                                    current_time = time.time()
                                    last_renewal = _token_renewal_cache.get(username, 0)
                                    time_since_last_renewal = (
                                        current_time - last_renewal
                                    )

                                    # Only renew if enough time has passed since last renewal
                                    if time_since_last_renewal >= _RENEWAL_MIN_INTERVAL:
                                        new_token = auth_handler.create_token(
                                            username=username,
                                            role=role,
                                            metadata=token_info.get("metadata", {}),
                                        )
                                        # Return new token via response header
                                        response.headers["X-New-Token"] = new_token

                                        # Update renewal cache
                                        _token_renewal_cache[username] = current_time

                                        # Optional: log renewal
                                        logger.info(
                                            f"Token auto-renewed for user {username} "
                                            f"(role: {role}, remaining: {remaining_seconds:.0f}s)"
                                        )
                                    else:
                                        # Log skip due to rate limit
                                        logger.debug(
                                            f"Token renewal skipped for {username} "
                                            f"(rate limit: last renewal {time_since_last_renewal:.0f}s ago)"
                                        )
                                    # ========== End of Rate Limiting Check ==========
                        except Exception as e:
                            # Renewal failure should not affect normal request, just log
                            logger.warning(f"Token auto-renew failed: {e}")
                # ========== End of Token Auto-Renewal Logic ==========

                # Accept guest token if no auth is configured
                if not auth_configured and token_info.get("role") == "guest":
                    return
                # Accept non-guest token if auth is configured
                if auth_configured and token_info.get("role") != "guest":
                    return

                # Token validation failed, immediately return 401 error
                raise HTTPException(
                    status_code=status.HTTP_401_UNAUTHORIZED,
                    detail="Invalid token. Please login again.",
                )
            except HTTPException as e:
                # If already a 401 error, re-raise it
                if e.status_code == status.HTTP_401_UNAUTHORIZED:
                    raise
                # For other exceptions, continue processing

        # 3. Acept all request if no API protection needed
        if not auth_configured and not api_key_configured:
            return

        # 4. Validate API key if provided and API-Key authentication is configured
        if (
            api_key_configured
            and api_key_header_value
            and api_key_header_value == api_key
        ):
            return  # API key validation successful

        ### Authentication failed ####

        # if password authentication is configured but not provided, ensure 401 error if auth_configured
        if auth_configured and not token:
            raise HTTPException(
                status_code=status.HTTP_401_UNAUTHORIZED,
                detail="No credentials provided. Please login.",
            )

        # if api key is provided but validation failed
        if api_key_header_value:
            raise HTTPException(
                status_code=HTTP_403_FORBIDDEN,
                detail="Invalid API Key",
            )

        # if api_key_configured but not provided
        if api_key_configured and not api_key_header_value:
            raise HTTPException(
                status_code=HTTP_403_FORBIDDEN,
                detail="API Key required",
            )

        # Otherwise: refuse access and return 403 error
        raise HTTPException(
            status_code=HTTP_403_FORBIDDEN,
            detail="API Key required or login authentication required.",
        )

    return combined_dependency


def display_splash_screen(args: argparse.Namespace) -> None:
    """
    Display a colorful splash screen showing LightRAG server configuration

    Args:
        args: Parsed command line arguments
    """
    # Banner
    # Banner
    top_border = "╔══════════════════════════════════════════════════════════════╗"
    bottom_border = "╚══════════════════════════════════════════════════════════════╝"
    width = len(top_border) - 4  # width inside the borders

    line1_text = f"LightRAG Server v{core_version}/{api_version}"
    line2_text = "Fast, Lightweight RAG Server Implementation"

    line1 = f"║ {line1_text.center(width)} ║"
    line2 = f"║ {line2_text.center(width)} ║"

    banner = f"""
    {top_border}
    {line1}
    {line2}
    {bottom_border}
    """
    ASCIIColors.cyan(banner)

    # Server Configuration
    ASCIIColors.magenta("\n📡 Server Configuration:")
    ASCIIColors.white("    ├─ Host: ", end="")
    ASCIIColors.yellow(f"{args.host}")
    ASCIIColors.white("    ├─ Port: ", end="")
    ASCIIColors.yellow(f"{args.port}")
    ASCIIColors.white("    ├─ Workers: ", end="")
    ASCIIColors.yellow(f"{args.workers}")
    ASCIIColors.white("    ├─ Timeout: ", end="")
    ASCIIColors.yellow(f"{args.timeout}")
    ASCIIColors.white("    ├─ CORS Origins: ", end="")
    ASCIIColors.yellow(f"{args.cors_origins}")
    ASCIIColors.white("    ├─ SSL Enabled: ", end="")
    ASCIIColors.yellow(f"{args.ssl}")
    if args.ssl:
        ASCIIColors.white("    ├─ SSL Cert: ", end="")
        ASCIIColors.yellow(f"{args.ssl_certfile}")
        ASCIIColors.white("    ├─ SSL Key: ", end="")
        ASCIIColors.yellow(f"{args.ssl_keyfile}")
    ASCIIColors.white("    ├─ Ollama Emulating Model: ", end="")
    ASCIIColors.yellow(f"{ollama_server_infos.LIGHTRAG_MODEL}")
    ASCIIColors.white("    ├─ Log Level: ", end="")
    ASCIIColors.yellow(f"{args.log_level}")
    ASCIIColors.white("    ├─ Verbose Debug: ", end="")
    ASCIIColors.yellow(f"{args.verbose}")
    ASCIIColors.white("    ├─ API Key: ", end="")
    ASCIIColors.yellow("Set" if args.key else "Not Set")
    ASCIIColors.white("    └─ JWT Auth: ", end="")
    ASCIIColors.yellow("Enabled" if args.auth_accounts else "Disabled")

    # Directory Configuration
    ASCIIColors.magenta("\n📂 Directory Configuration:")
    ASCIIColors.white("    ├─ Working Directory: ", end="")
    ASCIIColors.yellow(f"{args.working_dir}")
    ASCIIColors.white("    └─ Input Directory: ", end="")
    ASCIIColors.yellow(f"{args.input_dir}")

    # LLM Configuration
    ASCIIColors.magenta("\n🤖 LLM Configuration:")
    ASCIIColors.white("    ├─ Binding: ", end="")
    ASCIIColors.yellow(f"{args.llm_binding}")
    ASCIIColors.white("    ├─ Host: ", end="")
    ASCIIColors.yellow(f"{args.llm_binding_host}")
    ASCIIColors.white("    ├─ Model: ", end="")
    ASCIIColors.yellow(f"{args.llm_model}")
    ASCIIColors.white("    ├─ Max Async for LLM: ", end="")
    ASCIIColors.yellow(f"{args.max_async}")
    ASCIIColors.white("    ├─ Summary Context Size: ", end="")
    ASCIIColors.yellow(f"{args.summary_context_size}")
    ASCIIColors.white("    ├─ LLM Cache Enabled: ", end="")
    ASCIIColors.yellow(f"{args.enable_llm_cache}")
    ASCIIColors.white("    └─ LLM Cache for Extraction Enabled: ", end="")
    ASCIIColors.yellow(f"{args.enable_llm_cache_for_extract}")

    # Embedding Configuration
    ASCIIColors.magenta("\n📊 Embedding Configuration:")
    ASCIIColors.white("    ├─ Binding: ", end="")
    ASCIIColors.yellow(f"{args.embedding_binding}")
    ASCIIColors.white("    ├─ Host: ", end="")
    ASCIIColors.yellow(f"{args.embedding_binding_host}")
    ASCIIColors.white("    ├─ Model: ", end="")
    ASCIIColors.yellow(f"{args.embedding_model}")
    ASCIIColors.white("    └─ Dimensions: ", end="")
    ASCIIColors.yellow(f"{args.embedding_dim}")

    # RAG Configuration
    ASCIIColors.magenta("\n⚙️ RAG Configuration:")
    ASCIIColors.white("    ├─ Summary Language: ", end="")
    ASCIIColors.yellow(f"{args.summary_language}")
    ASCIIColors.white("    ├─ Entity Types: ", end="")
    ASCIIColors.yellow(f"{args.entity_types}")
    ASCIIColors.white("    ├─ Max Parallel Insert: ", end="")
    ASCIIColors.yellow(f"{args.max_parallel_insert}")
    ASCIIColors.white("    ├─ Chunk Size: ", end="")
    ASCIIColors.yellow(f"{args.chunk_size}")
    ASCIIColors.white("    ├─ Chunk Overlap Size: ", end="")
    ASCIIColors.yellow(f"{args.chunk_overlap_size}")
    ASCIIColors.white("    ├─ Cosine Threshold: ", end="")
    ASCIIColors.yellow(f"{args.cosine_threshold}")
    ASCIIColors.white("    ├─ Top-K: ", end="")
    ASCIIColors.yellow(f"{args.top_k}")
    ASCIIColors.white("    └─ Force LLM Summary on Merge: ", end="")
    ASCIIColors.yellow(
        f"{get_env_value('FORCE_LLM_SUMMARY_ON_MERGE', DEFAULT_FORCE_LLM_SUMMARY_ON_MERGE, int)}"
    )

    # System Configuration
    ASCIIColors.magenta("\n💾 Storage Configuration:")
    ASCIIColors.white("    ├─ KV Storage: ", end="")
    ASCIIColors.yellow(f"{args.kv_storage}")
    ASCIIColors.white("    ├─ Vector Storage: ", end="")
    ASCIIColors.yellow(f"{args.vector_storage}")
    ASCIIColors.white("    ├─ Graph Storage: ", end="")
    ASCIIColors.yellow(f"{args.graph_storage}")
    ASCIIColors.white("    ├─ Document Status Storage: ", end="")
    ASCIIColors.yellow(f"{args.doc_status_storage}")
    ASCIIColors.white("    └─ Workspace: ", end="")
    ASCIIColors.yellow(f"{args.workspace if args.workspace else '-'}")

    # Server Status
    ASCIIColors.green("\n✨ Server starting up...\n")

    # Server Access Information
    protocol = "https" if args.ssl else "http"
    if args.host == "0.0.0.0":
        ASCIIColors.magenta("\n🌐 Server Access Information:")
        ASCIIColors.white("    ├─ WebUI (local): ", end="")
        ASCIIColors.yellow(f"{protocol}://localhost:{args.port}")
        ASCIIColors.white("    ├─ Remote Access: ", end="")
        ASCIIColors.yellow(f"{protocol}://<your-ip-address>:{args.port}")
        ASCIIColors.white("    ├─ API Documentation (local): ", end="")
        ASCIIColors.yellow(f"{protocol}://localhost:{args.port}/docs")
        ASCIIColors.white("    └─ Alternative Documentation (local): ", end="")
        ASCIIColors.yellow(f"{protocol}://localhost:{args.port}/redoc")

        ASCIIColors.magenta("\n📝 Note:")
        ASCIIColors.cyan("""    Since the server is running on 0.0.0.0:
    - Use 'localhost' or '127.0.0.1' for local access
    - Use your machine's IP address for remote access
    - To find your IP address:
      • Windows: Run 'ipconfig' in terminal
      • Linux/Mac: Run 'ifconfig' or 'ip addr' in terminal
    """)
    else:
        base_url = f"{protocol}://{args.host}:{args.port}"
        ASCIIColors.magenta("\n🌐 Server Access Information:")
        ASCIIColors.white("    ├─ WebUI (local): ", end="")
        ASCIIColors.yellow(f"{base_url}")
        ASCIIColors.white("    ├─ API Documentation: ", end="")
        ASCIIColors.yellow(f"{base_url}/docs")
        ASCIIColors.white("    └─ Alternative Documentation: ", end="")
        ASCIIColors.yellow(f"{base_url}/redoc")

    # Security Notice
    if args.key:
        ASCIIColors.yellow("\n⚠️  Security Notice:")
        ASCIIColors.white("""    API Key authentication is enabled.
    Make sure to include the X-API-Key header in all your requests.
    """)
    if args.auth_accounts:
        ASCIIColors.yellow("\n⚠️  Security Notice:")
        ASCIIColors.white("""    JWT authentication is enabled.
    Make sure to login before making the request, and include the 'Authorization' in the header.
    """)

    # Ensure splash output flush to system log
    sys.stdout.flush()