ismail/haikal
1
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
ismail 2025-05-26 17:10:51 +03:00
parent 97ebf23732
commit feb9204c16
2 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
haikalbot/langchain_ollama_integration_guide.md
View File

@ -22,8 +22,8 @@ Add the following to your Django settings.py file:
```python
# Ollama and LangChain settings
OLLAMA_BASE_URL = "http://localhost:11434" # Default Ollama API URL
OLLAMA_MODEL = "jais:13b" # Or your preferred model
OLLAMA_BASE_URL = "http://10.10.1.132:11434" # Default Ollama API URL
OLLAMA_MODEL = "qwen3:6b" # Or your preferred model
OLLAMA_TIMEOUT = 120 # Seconds
```
@ -46,10 +46,10 @@ def get_ollama_llm():
"""
try:
# Get settings from Django settings or use defaults
base_url = getattr(settings, 'OLLAMA_BASE_URL', 'http://localhost:11434')
model = getattr(settings, 'OLLAMA_MODEL', 'jais:13b')
base_url = getattr(settings, 'OLLAMA_BASE_URL', 'http://10.10.1.132:11434')
model = getattr(settings, 'OLLAMA_MODEL', 'qwen3:8b')
timeout = getattr(settings, 'OLLAMA_TIMEOUT', 120)
# Configure Ollama with appropriate parameters for Arabic
return Ollama(
base_url=base_url,
@ -74,14 +74,14 @@ def create_prompt_analyzer_chain(language='ar'):
llm = get_ollama_llm()
if not llm:
return None
# Define the prompt template based on language
if language == 'ar':
template = """
قم بتحليل الاستعلام التالي وتحديد نوع التحليل المطلوب ونماذج البيانات المستهدفة وأي معلمات استعلام.
الاستعلام: {prompt}
قم بتقديم إجابتك بتنسيق JSON كما يلي:
{{
"analysis_type": "count" أو "relationship" أو "performance" أو "statistics" أو "general",
@ -92,9 +92,9 @@ def create_prompt_analyzer_chain(language='ar'):
else:
template = """
Analyze the following prompt and determine the type of analysis required, target data models, and any query parameters.
Prompt: {prompt}
Provide your answer in JSON format as follows:
{
"analysis_type": "count" or "relationship" or "performance" or "statistics" or "general",
@ -102,13 +102,13 @@ def create_prompt_analyzer_chain(language='ar'):
"query_params": {"field1": "value1", "field2": "value2"}
}
"""
# Create the prompt template
prompt_template = PromptTemplate(
input_variables=["prompt"],
template=template
)
# Create and return the LLM chain
return LLMChain(llm=llm, prompt=prompt_template)
```
@ -124,12 +124,12 @@ import re
class ModelAnalystView(View):
# ... existing code ...
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
# We'll initialize chains on demand to avoid startup issues
self.prompt_analyzer_chains = {}
def _get_prompt_analyzer_chain(self, language='ar'):
"""
Get or create a prompt analyzer chain for the specified language.
@ -137,7 +137,7 @@ class ModelAnalystView(View):
if language not in self.prompt_analyzer_chains:
self.prompt_analyzer_chains[language] = create_prompt_analyzer_chain(language)
return self.prompt_analyzer_chains[language]
def _analyze_prompt_with_llm(self, prompt, language='ar'):
"""
Use LangChain and Ollama to analyze the prompt.
@ -148,10 +148,10 @@ class ModelAnalystView(View):
if not chain:
# Fallback to rule-based analysis if chain creation failed
return self._analyze_prompt_rule_based(prompt, language)
# Run the chain
result = chain.run(prompt=prompt)
# Parse the JSON result
# Find JSON content within the response (in case the LLM adds extra text)
json_match = re.search(r'({.*})', result.replace('\n', ' '), re.DOTALL)
@ -161,12 +161,12 @@ class ModelAnalystView(View):
else:
# Fallback to rule-based analysis
return self._analyze_prompt_rule_based(prompt, language)
except Exception as e:
logger.error(f"Error in LLM prompt analysis: {str(e)}")
# Fallback to rule-based analysis
return self._analyze_prompt_rule_based(prompt, language)
def _analyze_prompt_rule_based(self, prompt, language='ar'):
"""
Rule-based fallback for prompt analysis.
@ -177,19 +177,19 @@ class ModelAnalystView(View):
"target_models": target_models,
"query_params": query_params
}
def _process_prompt(self, prompt, user, dealer_id, language='ar'):
"""
Process the natural language prompt and generate insights.
"""
# ... existing code ...
# Use LLM for prompt analysis
analysis_result = self._analyze_prompt_with_llm(prompt, language)
analysis_type = analysis_result.get('analysis_type', 'general')
target_models = analysis_result.get('target_models', [])
query_params = analysis_result.get('query_params', {})
# ... rest of the method ...
```
@ -215,7 +215,7 @@ def test_ollama_connection():
if not llm:
print("Failed to initialize Ollama LLM")
return
# Test with Arabic prompt
arabic_prompt = "مرحبا، كيف حالك؟"
print(f"Testing Arabic prompt: {arabic_prompt}")
@ -232,7 +232,7 @@ def test_prompt_analysis():
if not chain:
print("Failed to create prompt analyzer chain")
return
# Test with an Arabic analysis prompt
analysis_prompt = "كم عدد السيارات التي لدينا؟"
print(f"Testing analysis prompt: {analysis_prompt}")

2
haikalbot/services/llm_service.py
View File

@ -13,7 +13,7 @@ logger = logging.getLogger(__name__)
def get_llm_instance():
try:
base_url = getattr(settings, 'OLLAMA_BASE_URL', 'http://localhost:11434')
base_url = getattr(settings, 'OLLAMA_BASE_URL', 'http://10.10.1.132:11434')
model = getattr(settings, 'OLLAMA_MODEL', 'qwen3:8b')
temperature = getattr(settings, 'OLLAMA_TEMPERATURE', 0.2)
top_p = getattr(settings, 'OLLAMA_TOP_P', 0.8)