File size: 4,827 Bytes
b6fa51d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ef93124
 
a226579
 
 
 
 
ef93124
b6fa51d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c8f7f2e
 
 
 
b6fa51d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
Pydantic Models for API Request/Response

Defines the data structures for API communication.
"""

from typing import List, Optional, Dict, Any
from pydantic import BaseModel, Field


# ============== Query Models ==============

class QueryRequest(BaseModel):
    """Request model for query endpoint."""
    question: str = Field(
        ...,
        description="The question to ask about the documents",
        min_length=1,
        max_length=2000,
        examples=["What is the refund policy?"]
    )
    collection_name: str = Field(
        default="documents",
        description="Name of the document collection to search"
    )
    top_k: int = Field(
        default=5,
        description="Number of documents to retrieve",
        ge=1,
        le=20
    )
    include_sources: bool = Field(
        default=True,
        description="Whether to include source documents in response"
    )
    api_key: Optional[str] = Field(
        default=None,
        description="User-provided API key (BYOK)"
    )
    provider: str = Field(
        default="gemini",
        description="LLM provider: gemini, openai, anthropic, groq"
    )


class SourceDocument(BaseModel):
    """A source document used in the answer."""
    content: str = Field(..., description="Document content snippet")
    metadata: Dict[str, Any] = Field(
        default_factory=dict,
        description="Document metadata"
    )
    score: Optional[float] = Field(
        None,
        description="Relevance score"
    )


class QueryResponse(BaseModel):
    """Response model for query endpoint."""
    answer: str = Field(..., description="Generated answer")
    question: str = Field(..., description="Original question")
    sources: Optional[List[SourceDocument]] = Field(
        None,
        description="Source documents used"
    )
    num_sources: Optional[int] = Field(
        None,
        description="Number of sources used"
    )
    cached: bool = Field(
        default=False,
        description="Whether this response was served from cache"
    )


# ============== Ingest Models ==============

class IngestRequest(BaseModel):
    """Request model for file ingestion."""
    collection_name: str = Field(
        default="documents",
        description="Name of the collection to ingest into"
    )
    chunk_size: int = Field(
        default=1000,
        description="Size of document chunks",
        ge=100,
        le=4000
    )
    chunk_overlap: int = Field(
        default=200,
        description="Overlap between chunks",
        ge=0,
        le=500
    )


class IngestResponse(BaseModel):
    """Response model for ingestion endpoint."""
    success: bool = Field(..., description="Whether ingestion succeeded")
    message: str = Field(..., description="Status message")
    documents_processed: int = Field(
        default=0,
        description="Number of documents processed"
    )
    chunks_created: int = Field(
        default=0,
        description="Number of chunks created"
    )
    collection_name: str = Field(
        ...,
        description="Collection documents were added to"
    )


class IngestTextRequest(BaseModel):
    """Request model for text ingestion."""
    text: str = Field(
        ...,
        description="Text content to ingest",
        min_length=1,
        max_length=100000
    )
    metadata: Dict[str, Any] = Field(
        default_factory=dict,
        description="Optional metadata for the document"
    )
    collection_name: str = Field(
        default="documents",
        description="Name of the collection"
    )


# ============== Health Models ==============

class HealthResponse(BaseModel):
    """Response model for health check."""
    status: str = Field(..., description="Health status")
    version: str = Field(..., description="API version")
    environment: str = Field(..., description="Environment name")


class ComponentHealth(BaseModel):
    """Health status of a component."""
    name: str = Field(..., description="Component name")
    status: str = Field(..., description="Component status")
    details: Optional[str] = Field(None, description="Additional details")


class DetailedHealthResponse(BaseModel):
    """Detailed health check response."""
    status: str = Field(..., description="Overall status")
    version: str = Field(..., description="API version")
    components: List[ComponentHealth] = Field(
        ...,
        description="Component health statuses"
    )


# ============== Error Models ==============

class ErrorResponse(BaseModel):
    """Standard error response."""
    error: str = Field(..., description="Error type")
    message: str = Field(..., description="Error message")
    details: Optional[Dict[str, Any]] = Field(
        None,
        description="Additional error details"
    )