File size: 11,478 Bytes
f75cf19
e3e3a84
 
 
c4b28eb
e3e3a84
 
 
 
 
 
 
c4b28eb
e3e3a84
 
 
 
 
 
 
c4b28eb
7793bb6
ffa0f3d
aff5d04
ffa0f3d
89aa2b4
 
 
 
 
 
ffa0f3d
7793bb6
aff5d04
 
 
a3dfc07
ffa0f3d
a3dfc07
 
aff5d04
a3dfc07
ffa0f3d
7793bb6
aff5d04
7793bb6
aff5d04
 
 
 
 
 
 
a3dfc07
 
 
 
aff5d04
a3dfc07
aff5d04
 
 
57abf2f
 
aff5d04
 
7793bb6
ffa0f3d
7793bb6
ffa0f3d
 
500761d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c280a92
 
 
 
508a7e5
c280a92
 
 
 
 
 
 
508a7e5
 
 
 
 
 
c280a92
 
 
 
 
 
 
 
 
508a7e5
 
 
c280a92
 
 
 
 
508a7e5
 
 
c280a92
 
 
 
 
 
 
 
 
 
 
 
 
 
 
508a7e5
 
c280a92
 
 
 
 
508a7e5
c280a92
 
508a7e5
c280a92
 
508a7e5
c280a92
 
508a7e5
c280a92
 
508a7e5
 
 
 
 
 
 
 
 
 
c280a92
 
 
 
508a7e5
 
 
 
 
 
c280a92
 
 
 
 
508a7e5
c280a92
 
508a7e5
 
 
c280a92
 
508a7e5
c280a92
 
 
 
 
508a7e5
 
 
 
c280a92
 
 
 
 
 
508a7e5
c280a92
 
 
 
 
 
 
 
508a7e5
 
c280a92
 
 
 
 
508a7e5
c280a92
 
 
 
508a7e5
c280a92
 
 
508a7e5
c280a92
 
 
 
 
 
 
508a7e5
c280a92
508a7e5
 
 
 
 
 
 
 
 
 
 
 
 
 
c280a92
508a7e5
 
 
c280a92
 
508a7e5
 
 
 
c280a92
 
e3e3a84
 
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
from flask import Flask, jsonify, render_template, request

app = Flask(__name__)


@app.route("/")
def index():
    """
    Renders the main page.
    """
    return render_template("index.html")


@app.route("/health")
def health():
    """
    Health check endpoint.
    """
    return jsonify({"status": "ok"}), 200


@app.route("/ingest", methods=["POST"])
def ingest():
    """Endpoint to trigger document ingestion with embeddings"""
    try:
        from src.config import (
            CORPUS_DIRECTORY,
            DEFAULT_CHUNK_SIZE,
            DEFAULT_OVERLAP,
            RANDOM_SEED,
        )
        from src.ingestion.ingestion_pipeline import IngestionPipeline

        # Get optional parameters from request
        data = request.get_json() if request.is_json else {}
        store_embeddings = data.get("store_embeddings", True)

        pipeline = IngestionPipeline(
            chunk_size=DEFAULT_CHUNK_SIZE,
            overlap=DEFAULT_OVERLAP,
            seed=RANDOM_SEED,
            store_embeddings=store_embeddings,
        )

        result = pipeline.process_directory_with_embeddings(CORPUS_DIRECTORY)

        # Create response with enhanced information
        response = {
            "status": result["status"],
            "chunks_processed": result["chunks_processed"],
            "files_processed": result["files_processed"],
            "embeddings_stored": result["embeddings_stored"],
            "store_embeddings": result["store_embeddings"],
            "message": (
                f"Successfully processed {result['chunks_processed']} chunks "
                f"from {result['files_processed']} files"
            ),
        }

        # Include failed files info if any
        if result["failed_files"]:
            response["failed_files"] = result["failed_files"]
            failed_count = len(result["failed_files"])
            response["warnings"] = f"{failed_count} files failed to process"

        return jsonify(response)

    except Exception as e:
        return jsonify({"status": "error", "message": str(e)}), 500


@app.route("/search", methods=["POST"])
def search():
    """
    Endpoint to perform semantic search on ingested documents.

    Accepts JSON requests with query text and optional parameters.
    Returns semantically similar document chunks.
    """
    try:
        # Validate request contains JSON data
        if not request.is_json:
            return (
                jsonify(
                    {
                        "status": "error",
                        "message": "Content-Type must be application/json",
                    }
                ),
                400,
            )

        data = request.get_json()

        # Validate required query parameter
        query = data.get("query")
        if query is None:
            return (
                jsonify({"status": "error", "message": "Query parameter is required"}),
                400,
            )

        if not isinstance(query, str) or not query.strip():
            return (
                jsonify(
                    {"status": "error", "message": "Query must be a non-empty string"}
                ),
                400,
            )

        # Extract optional parameters with defaults
        top_k = data.get("top_k", 5)
        threshold = data.get("threshold", 0.3)

        # Validate parameters
        if not isinstance(top_k, int) or top_k <= 0:
            return (
                jsonify(
                    {"status": "error", "message": "top_k must be a positive integer"}
                ),
                400,
            )

        if not isinstance(threshold, (int, float)) or not (0.0 <= threshold <= 1.0):
            return (
                jsonify(
                    {
                        "status": "error",
                        "message": "threshold must be a number between 0 and 1",
                    }
                ),
                400,
            )

        # Initialize search components
        from src.config import COLLECTION_NAME, VECTOR_DB_PERSIST_PATH
        from src.embedding.embedding_service import EmbeddingService
        from src.search.search_service import SearchService
        from src.vector_store.vector_db import VectorDatabase

        vector_db = VectorDatabase(VECTOR_DB_PERSIST_PATH, COLLECTION_NAME)
        embedding_service = EmbeddingService()
        search_service = SearchService(vector_db, embedding_service)

        # Perform search
        results = search_service.search(
            query=query.strip(), top_k=top_k, threshold=threshold
        )

        # Format response
        response = {
            "status": "success",
            "query": query.strip(),
            "results_count": len(results),
            "results": results,
        }

        return jsonify(response)

    except ValueError as e:
        return jsonify({"status": "error", "message": str(e)}), 400

    except Exception as e:
        return jsonify({"status": "error", "message": f"Search failed: {str(e)}"}), 500


@app.route("/chat", methods=["POST"])
def chat():
    """
    Endpoint for conversational RAG interactions.

    Accepts JSON requests with user messages and returns AI-generated
    responses based on corporate policy documents.
    """
    try:
        # Validate request contains JSON data
        if not request.is_json:
            return (
                jsonify(
                    {
                        "status": "error",
                        "message": "Content-Type must be application/json",
                    }
                ),
                400,
            )

        data = request.get_json()

        # Validate required message parameter
        message = data.get("message")
        if message is None:
            return (
                jsonify(
                    {"status": "error", "message": "message parameter is required"}
                ),
                400,
            )

        if not isinstance(message, str) or not message.strip():
            return (
                jsonify(
                    {"status": "error", "message": "message must be a non-empty string"}
                ),
                400,
            )

        # Extract optional parameters
        conversation_id = data.get("conversation_id")
        include_sources = data.get("include_sources", True)
        include_debug = data.get("include_debug", False)

        # Initialize RAG pipeline components
        try:
            from src.config import COLLECTION_NAME, VECTOR_DB_PERSIST_PATH
            from src.embedding.embedding_service import EmbeddingService
            from src.llm.llm_service import LLMService
            from src.rag.rag_pipeline import RAGPipeline
            from src.rag.response_formatter import ResponseFormatter
            from src.search.search_service import SearchService
            from src.vector_store.vector_db import VectorDatabase

            # Initialize services
            vector_db = VectorDatabase(VECTOR_DB_PERSIST_PATH, COLLECTION_NAME)
            embedding_service = EmbeddingService()
            search_service = SearchService(vector_db, embedding_service)

            # Initialize LLM service from environment
            llm_service = LLMService.from_environment()

            # Initialize RAG pipeline
            rag_pipeline = RAGPipeline(search_service, llm_service)

            # Initialize response formatter
            formatter = ResponseFormatter()

        except ValueError as e:
            return (
                jsonify(
                    {
                        "status": "error",
                        "message": f"LLM service configuration error: {str(e)}",
                        "details": (
                            "Please ensure OPENROUTER_API_KEY or GROQ_API_KEY "
                            "environment variables are set"
                        ),
                    }
                ),
                503,
            )
        except Exception as e:
            return (
                jsonify(
                    {
                        "status": "error",
                        "message": f"Service initialization failed: {str(e)}",
                    }
                ),
                500,
            )

        # Generate RAG response
        rag_response = rag_pipeline.generate_answer(message.strip())

        # Format response for API
        if include_sources:
            formatted_response = formatter.format_api_response(
                rag_response, include_debug
            )
        else:
            formatted_response = formatter.format_chat_response(
                rag_response, conversation_id, include_sources=False
            )

        return jsonify(formatted_response)

    except Exception as e:
        return (
            jsonify({"status": "error", "message": f"Chat request failed: {str(e)}"}),
            500,
        )


@app.route("/chat/health", methods=["GET"])
def chat_health():
    """
    Health check endpoint for RAG chat functionality.

    Returns the status of all RAG pipeline components.
    """
    try:
        from src.config import COLLECTION_NAME, VECTOR_DB_PERSIST_PATH
        from src.embedding.embedding_service import EmbeddingService
        from src.llm.llm_service import LLMService
        from src.rag.rag_pipeline import RAGPipeline
        from src.rag.response_formatter import ResponseFormatter
        from src.search.search_service import SearchService
        from src.vector_store.vector_db import VectorDatabase

        # Initialize services for health check
        vector_db = VectorDatabase(VECTOR_DB_PERSIST_PATH, COLLECTION_NAME)
        embedding_service = EmbeddingService()
        search_service = SearchService(vector_db, embedding_service)

        try:
            llm_service = LLMService.from_environment()
            rag_pipeline = RAGPipeline(search_service, llm_service)
            formatter = ResponseFormatter()

            # Perform health check
            health_data = rag_pipeline.health_check()
            health_response = formatter.create_health_response(health_data)

            # Determine HTTP status based on health
            if health_data.get("pipeline") == "healthy":
                return jsonify(health_response), 200
            elif health_data.get("pipeline") == "degraded":
                return jsonify(health_response), 200  # Still functional
            else:
                return jsonify(health_response), 503  # Service unavailable

        except ValueError as e:
            return (
                jsonify(
                    {
                        "status": "error",
                        "message": f"LLM configuration error: {str(e)}",
                        "health": {
                            "pipeline_status": "unhealthy",
                            "components": {
                                "llm_service": {
                                    "status": "unconfigured",
                                    "error": str(e),
                                }
                            },
                        },
                    }
                ),
                503,
            )

    except Exception as e:
        return (
            jsonify({"status": "error", "message": f"Health check failed: {str(e)}"}),
            500,
        )


if __name__ == "__main__":
    app.run(debug=True)