feat: Add Aktenzeichen utility functions and LangChain xAI service integration
- Implemented utility functions for extracting, validating, and normalizing Aktenzeichen in 'aktenzeichen_utils.py'. - Created LangChainXAIService for integrating LangChain ChatXAI with file search capabilities in 'langchain_xai_service.py'. - Developed VMH xAI Chat Completions API to handle OpenAI-compatible requests with support for Aktenzeichen detection and file search in 'xai_chat_completion_api_step.py'.
This commit is contained in:
bsiggel
110
services/aktenzeichen_utils.py
Normal file
110
services/aktenzeichen_utils.py
Normal file
@@ -0,0 +1,110 @@
|
||||
"""Aktenzeichen-Erkennung und Validation
|
||||
|
||||
Utility functions für das Erkennen, Validieren und Normalisieren von
|
||||
Aktenzeichen im Format '1234/56' oder 'ABC/23'.
|
||||
"""
|
||||
import re
|
||||
from typing import Optional
|
||||
|
||||
|
||||
# Regex für Aktenzeichen: 1-4 Zeichen (alphanumerisch) + "/" + 2 Ziffern
|
||||
AKTENZEICHEN_REGEX = re.compile(r'^([A-Za-z0-9]{1,4}/\d{2})\s*', re.IGNORECASE)
|
||||
|
||||
|
||||
def extract_aktenzeichen(text: str) -> Optional[str]:
|
||||
"""
|
||||
Extrahiert Aktenzeichen vom Anfang des Textes.
|
||||
|
||||
Pattern: ^[A-Za-z0-9]{1,4}/\d{2}
|
||||
|
||||
Examples:
|
||||
>>> extract_aktenzeichen("1234/56 Was ist der Stand?")
|
||||
"1234/56"
|
||||
>>> extract_aktenzeichen("ABC/23 Frage zum Vertrag")
|
||||
"ABC/23"
|
||||
>>> extract_aktenzeichen("Kein Aktenzeichen hier")
|
||||
None
|
||||
|
||||
Args:
|
||||
text: Eingabetext (z.B. erste Message)
|
||||
|
||||
Returns:
|
||||
Aktenzeichen als String, oder None wenn nicht gefunden
|
||||
"""
|
||||
if not text or not isinstance(text, str):
|
||||
return None
|
||||
|
||||
match = AKTENZEICHEN_REGEX.match(text.strip())
|
||||
return match.group(1) if match else None
|
||||
|
||||
|
||||
def remove_aktenzeichen(text: str) -> str:
|
||||
"""
|
||||
Entfernt Aktenzeichen vom Anfang des Textes.
|
||||
|
||||
Examples:
|
||||
>>> remove_aktenzeichen("1234/56 Was ist der Stand?")
|
||||
"Was ist der Stand?"
|
||||
>>> remove_aktenzeichen("Kein Aktenzeichen")
|
||||
"Kein Aktenzeichen"
|
||||
|
||||
Args:
|
||||
text: Eingabetext mit Aktenzeichen
|
||||
|
||||
Returns:
|
||||
Text ohne Aktenzeichen (whitespace getrimmt)
|
||||
"""
|
||||
if not text or not isinstance(text, str):
|
||||
return text
|
||||
|
||||
return AKTENZEICHEN_REGEX.sub('', text, count=1).strip()
|
||||
|
||||
|
||||
def validate_aktenzeichen(az: str) -> bool:
|
||||
"""
|
||||
Validiert Aktenzeichen-Format.
|
||||
|
||||
Pattern: ^[A-Za-z0-9]{1,4}/\d{2}$
|
||||
|
||||
Examples:
|
||||
>>> validate_aktenzeichen("1234/56")
|
||||
True
|
||||
>>> validate_aktenzeichen("ABC/23")
|
||||
True
|
||||
>>> validate_aktenzeichen("12345/567") # Zu lang
|
||||
False
|
||||
>>> validate_aktenzeichen("1234-56") # Falsches Trennzeichen
|
||||
False
|
||||
|
||||
Args:
|
||||
az: Aktenzeichen zum Validieren
|
||||
|
||||
Returns:
|
||||
True wenn valide, False sonst
|
||||
"""
|
||||
if not az or not isinstance(az, str):
|
||||
return False
|
||||
|
||||
return bool(re.match(r'^[A-Za-z0-9]{1,4}/\d{2}$', az, re.IGNORECASE))
|
||||
|
||||
|
||||
def normalize_aktenzeichen(az: str) -> str:
|
||||
"""
|
||||
Normalisiert Aktenzeichen (uppercase, trim whitespace).
|
||||
|
||||
Examples:
|
||||
>>> normalize_aktenzeichen("abc/23")
|
||||
"ABC/23"
|
||||
>>> normalize_aktenzeichen(" 1234/56 ")
|
||||
"1234/56"
|
||||
|
||||
Args:
|
||||
az: Aktenzeichen zum Normalisieren
|
||||
|
||||
Returns:
|
||||
Normalisiertes Aktenzeichen (uppercase, getrimmt)
|
||||
"""
|
||||
if not az or not isinstance(az, str):
|
||||
return az
|
||||
|
||||
return az.strip().upper()
|
||||
162
services/langchain_xai_service.py
Normal file
162
services/langchain_xai_service.py
Normal file
@@ -0,0 +1,162 @@
|
||||
"""LangChain xAI Integration Service
|
||||
|
||||
Service für LangChain ChatXAI Integration mit File Search Binding.
|
||||
Analog zu xai_service.py für xAI Files API.
|
||||
"""
|
||||
import os
|
||||
from typing import Dict, List, Any, Optional, AsyncIterator
|
||||
from services.logging_utils import get_service_logger
|
||||
|
||||
|
||||
class LangChainXAIService:
|
||||
"""
|
||||
Wrapper für LangChain ChatXAI mit Motia-Integration.
|
||||
|
||||
Benötigte Umgebungsvariablen:
|
||||
- XAI_API_KEY: API Key für xAI (für ChatXAI model)
|
||||
|
||||
Usage:
|
||||
service = LangChainXAIService(ctx)
|
||||
model = service.get_chat_model(model="grok-2-latest")
|
||||
model_with_tools = service.bind_file_search(model, collection_id)
|
||||
result = await service.invoke_chat(model_with_tools, messages)
|
||||
"""
|
||||
|
||||
def __init__(self, ctx=None):
|
||||
"""
|
||||
Initialize LangChain xAI Service.
|
||||
|
||||
Args:
|
||||
ctx: Optional Motia context for logging
|
||||
|
||||
Raises:
|
||||
ValueError: If XAI_API_KEY not configured
|
||||
"""
|
||||
self.api_key = os.getenv('XAI_API_KEY', '')
|
||||
self.ctx = ctx
|
||||
self.logger = get_service_logger('langchain_xai', ctx)
|
||||
|
||||
if not self.api_key:
|
||||
raise ValueError("XAI_API_KEY not configured in environment")
|
||||
|
||||
def _log(self, msg: str, level: str = 'info') -> None:
|
||||
"""Delegate logging to service logger"""
|
||||
log_func = getattr(self.logger, level, self.logger.info)
|
||||
log_func(msg)
|
||||
|
||||
def get_chat_model(
|
||||
self,
|
||||
model: str = "grok-2-latest",
|
||||
temperature: float = 0.7,
|
||||
max_tokens: Optional[int] = None
|
||||
):
|
||||
"""
|
||||
Initialisiert ChatXAI Model.
|
||||
|
||||
Args:
|
||||
model: Model name (default: grok-2-latest)
|
||||
temperature: Sampling temperature 0.0-1.0
|
||||
max_tokens: Optional max tokens for response
|
||||
|
||||
Returns:
|
||||
ChatXAI model instance
|
||||
|
||||
Raises:
|
||||
ImportError: If langchain_xai not installed
|
||||
"""
|
||||
try:
|
||||
from langchain_xai import ChatXAI
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"langchain_xai not installed. "
|
||||
"Run: pip install langchain-xai>=0.2.0"
|
||||
)
|
||||
|
||||
self._log(f"🤖 Initializing ChatXAI: model={model}, temp={temperature}")
|
||||
|
||||
kwargs = {
|
||||
"model": model,
|
||||
"api_key": self.api_key,
|
||||
"temperature": temperature
|
||||
}
|
||||
if max_tokens:
|
||||
kwargs["max_tokens"] = max_tokens
|
||||
|
||||
return ChatXAI(**kwargs)
|
||||
|
||||
def bind_file_search(
|
||||
self,
|
||||
model,
|
||||
collection_id: str,
|
||||
max_num_results: int = 10
|
||||
):
|
||||
"""
|
||||
Bindet xAI file_search Tool an Model.
|
||||
|
||||
Args:
|
||||
model: ChatXAI model instance
|
||||
collection_id: xAI Collection ID (vector store)
|
||||
max_num_results: Max results from file search (default: 10)
|
||||
|
||||
Returns:
|
||||
Model with bound file_search tool
|
||||
"""
|
||||
self._log(f"🔍 Binding file_search: collection={collection_id}, max_results={max_num_results}")
|
||||
|
||||
tools = [{
|
||||
"type": "file_search",
|
||||
"vector_store_ids": [collection_id],
|
||||
"max_num_results": max_num_results
|
||||
}]
|
||||
|
||||
return model.bind_tools(tools)
|
||||
|
||||
async def invoke_chat(
|
||||
self,
|
||||
model,
|
||||
messages: List[Dict[str, Any]]
|
||||
) -> Any:
|
||||
"""
|
||||
Non-streaming Chat Completion.
|
||||
|
||||
Args:
|
||||
model: ChatXAI model (with or without tools)
|
||||
messages: List of message dicts [{"role": "user", "content": "..."}]
|
||||
|
||||
Returns:
|
||||
LangChain AIMessage with response
|
||||
|
||||
Raises:
|
||||
Exception: If API call fails
|
||||
"""
|
||||
self._log(f"💬 Invoking chat: {len(messages)} messages", level='debug')
|
||||
|
||||
result = await model.ainvoke(messages)
|
||||
|
||||
self._log(f"✅ Response received: {len(result.content)} chars", level='debug')
|
||||
return result
|
||||
|
||||
async def astream_chat(
|
||||
self,
|
||||
model,
|
||||
messages: List[Dict[str, Any]]
|
||||
) -> AsyncIterator:
|
||||
"""
|
||||
Streaming Chat Completion.
|
||||
|
||||
Args:
|
||||
model: ChatXAI model (with or without tools)
|
||||
messages: List of message dicts
|
||||
|
||||
Yields:
|
||||
Chunks from streaming response
|
||||
|
||||
Example:
|
||||
async for chunk in service.astream_chat(model, messages):
|
||||
delta = chunk.content if hasattr(chunk, "content") else ""
|
||||
# Process delta...
|
||||
"""
|
||||
self._log(f"💬 Streaming chat: {len(messages)} messages", level='debug')
|
||||
|
||||
async for chunk in model.astream(messages):
|
||||
yield chunk
|
||||
Reference in New Issue
Block a user