ragaai-catalyst 2.0.7.2b0__tar.gz → 2.0.7.2b1__tar.gz

{ragaai_catalyst-2.0.7.2b0 → ragaai_catalyst-2.0.7.2b1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ragaai_catalyst
-Version: 2.0.7.2b0
+Version: 2.0.7.2b1
 Summary: RAGA AI CATALYST
 Author-email: Kiran Scaria <kiran.scaria@raga.ai>, Kedar Gaikwad <kedar.gaikwad@raga.ai>, Dushyant Mahajan <dushyant.mahajan@raga.ai>, Siddhartha Kosti <siddhartha.kosti@raga.ai>, Ritika Goel <ritika.goel@raga.ai>, Vijay Chaurasia <vijay.chaurasia@raga.ai>
 Requires-Python: >=3.9

{ragaai_catalyst-2.0.7.2b0 → ragaai_catalyst-2.0.7.2b1}/pyproject.toml

@@ -8,7 +8,7 @@ description = "RAGA AI CATALYST"
 readme = "README.md"
 requires-python = ">=3.9"
 # license = {file = "LICENSE"}
-version = "2.0.7.2.beta.0"
+version = "2.0.7.2.beta.1"
 authors = [
     {name = "Kiran Scaria", email = "kiran.scaria@raga.ai"},
     {name = "Kedar Gaikwad", email = "kedar.gaikwad@raga.ai"},

{ragaai_catalyst-2.0.7.2b0 → ragaai_catalyst-2.0.7.2b1}/ragaai_catalyst/tracers/llamaindex_callback.py

@@ -11,6 +11,7 @@ import tempfile
 
 from ..ragaai_catalyst import RagaAICatalyst
 
+
 class CustomEncoder(json.JSONEncoder):
     def default(self, obj):
         if isinstance(obj, Enum):
@@ -54,7 +55,7 @@ class LlamaIndexTracer:
                 payload: Optional[Dict[str, Any]] = None,
                 event_id: str = "",
                 parent_id: str = "",
-                **kwargs: Any
+                **kwargs: Any,
             ) -> None:
                 trace = {
                     "event_type": event_type,
@@ -68,7 +69,7 @@ class LlamaIndexTracer:
                     self.in_query = True
                     self.query_event_id = event_id
                     self.current_query_traces = []
-                
+
                 if self.in_query:
                     self.current_query_traces.append(trace)
                 self.traces.append(trace)
@@ -78,7 +79,7 @@ class LlamaIndexTracer:
                 event_type: Optional[str],
                 payload: Optional[Dict[str, Any]] = None,
                 event_id: str = "",
-                **kwargs: Any
+                **kwargs: Any,
             ) -> None:
                 trace = {
                     "event_type": event_type,
@@ -90,24 +91,21 @@ class LlamaIndexTracer:
                 if self.in_query:
                     self.current_query_traces.append(trace)
                 self.traces.append(trace)
-                
+
                 # If this is the end of a query event, automatically save the traces
                 if event_type == "query" and event_id == self.query_event_id:
                     self.in_query = False
                     outer_self._save_current_query_traces(self.current_query_traces)
                     self.current_query_traces = []
-                
 
         self.trace_handler = CustomTraceHandler()
         self.callback_manager.add_handler(self.trace_handler)
         Settings.callback_manager = self.callback_manager
 
-
         # Monkey-patch LlamaIndex components
         self._monkey_patch()
         return self  # Return self to allow method chaining
 
-
     def _save_current_query_traces(self, query_traces):
         """Save traces for the current query"""
         self.query_count += 1
@@ -131,7 +129,6 @@ class LlamaIndexTracer:
         self._insert_traces(presignedUrl)
         # print(f"Query {self.query_count} traces uploaded")
 
-
     def _monkey_patch(self):
         """Monkey-patch LlamaIndex components to automatically include the callback manager"""
         from llama_index.core import VectorStoreIndex, ServiceContext
@@ -181,7 +178,7 @@ class LlamaIndexTracer:
         # self._upload_traces(save_json_to_pwd=True)
         self.callback_manager.remove_handler(self.trace_handler)
         self._restore_original_inits()
-        print("Traces uplaoded")
+        print("Traces uploaded")
         self._upload_task = True
 
     def _restore_original_inits(self):
@@ -213,17 +210,17 @@ class LlamaIndexTracer:
         Generate a random trace ID using UUID4.
         Returns a string representation of the UUID with no hyphens.
         """
-        return '0x'+str(uuid.uuid4()).replace('-', '')
+        return "0x" + str(uuid.uuid4()).replace("-", "")
 
     def _get_user_passed_detail(self):
         user_detail = self.user_detail
         user_detail["trace_id"] = self._generate_trace_id()
         metadata = user_detail["metadata"]
         metadata["log_source"] = "llamaindex_tracer"
-        metadata["recorded_on"] = datetime.utcnow().isoformat().replace('T', ' ')
+        metadata["recorded_on"] = datetime.utcnow().isoformat().replace("T", " ")
         user_detail["metadata"] = metadata
         return user_detail
-    
+
     def _add_traces_in_data(self, traces=None):
         """Add traces to user detail"""
         user_detail = self._get_user_passed_detail()
@@ -234,37 +231,40 @@ class LlamaIndexTracer:
         user_detail["traces"] = traces
         return user_detail
 
-
     def _create_dataset_schema_with_trace(self):
         SCHEMA_MAPPING_NEW = {
             "trace_id": {"columnType": "traceId"},
             "trace_uri": {"columnType": "traceUri"},
             "prompt": {"columnType": "prompt"},
-            "response":{"columnType": "response"},
+            "response": {"columnType": "response"},
             "context": {"columnType": "context"},
-            "llm_model": {"columnType":"pipeline"},
+            "llm_model": {"columnType": "pipeline"},
             "recorded_on": {"columnType": "metadata"},
-            "embed_model": {"columnType":"pipeline"},
+            "embed_model": {"columnType": "pipeline"},
             "log_source": {"columnType": "metadata"},
-            "vector_store":{"columnType":"pipeline"},
-            "feedback": {"columnType":"feedBack"}
+            "vector_store": {"columnType": "pipeline"},
+            "feedback": {"columnType": "feedBack"},
         }
+
         def make_request():
             headers = {
                 "Content-Type": "application/json",
                 "Authorization": f"Bearer {os.getenv('RAGAAI_CATALYST_TOKEN')}",
                 "X-Project-Name": self.project_name,
             }
-            payload = json.dumps({
-                "datasetName": self.dataset_name,
-                "schemaMapping": SCHEMA_MAPPING_NEW,
-                "traceFolderUrl": None,
-            })
-            response = requests.request("POST",
+            payload = json.dumps(
+                {
+                    "datasetName": self.dataset_name,
+                    "schemaMapping": SCHEMA_MAPPING_NEW,
+                    "traceFolderUrl": None,
+                }
+            )
+            response = requests.request(
+                "POST",
                 f"{self.base_url}/v1/llm/dataset/logs",
                 headers=headers,
                 data=payload,
-                timeout=self.timeout
+                timeout=self.timeout,
             )
 
             return response
@@ -277,31 +277,35 @@ class LlamaIndexTracer:
         if response.status_code != 200:
             return response.status_code
         return response.status_code
-    
+
     def _get_presigned_url(self):
-        payload = json.dumps({
+        payload = json.dumps(
+            {
                 "datasetName": self.dataset_name,
                 "numFiles": 1,
-            })
+            }
+        )
         headers = {
             "Content-Type": "application/json",
             "Authorization": f"Bearer {os.getenv('RAGAAI_CATALYST_TOKEN')}",
             "X-Project-Name": self.project_name,
         }
 
-        response = requests.request("GET", 
-                                    f"{self.base_url}/v1/llm/presigned-url", 
-                                    headers=headers, 
-                                    data=payload,
-                                    timeout=self.timeout)
+        response = requests.request(
+            "GET",
+            f"{self.base_url}/v1/llm/presigned-url",
+            headers=headers,
+            data=payload,
+            timeout=self.timeout,
+        )
         if response.status_code == 200:
             presignedUrls = response.json()["data"]["presignedUrls"][0]
             return presignedUrls
-        
+
     def _put_presigned_url(self, presignedUrl, filename):
         headers = {
-                "Content-Type": "application/json",
-            }
+            "Content-Type": "application/json",
+        }
 
         if "blob.core.windows.net" in presignedUrl:  # Azure
             headers["x-ms-blob-type"] = "BlockBlob"
@@ -309,31 +313,31 @@ class LlamaIndexTracer:
         with open(filename) as f:
             payload = f.read().replace("\n", "").replace("\r", "").encode()
 
-
-        response = requests.request("PUT", 
-                                    presignedUrl, 
-                                    headers=headers, 
-                                    data=payload,
-                                    timeout=self.timeout)
+        response = requests.request(
+            "PUT", presignedUrl, headers=headers, data=payload, timeout=self.timeout
+        )
         if response.status_code != 200 or response.status_code != 201:
             return response, response.status_code
-    
+
     def _insert_traces(self, presignedUrl):
         headers = {
-                "Authorization": f"Bearer {os.getenv('RAGAAI_CATALYST_TOKEN')}",
-                "Content-Type": "application/json",
-                "X-Project-Name": self.project_name,
-            }
-        payload = json.dumps({
+            "Authorization": f"Bearer {os.getenv('RAGAAI_CATALYST_TOKEN')}",
+            "Content-Type": "application/json",
+            "X-Project-Name": self.project_name,
+        }
+        payload = json.dumps(
+            {
                 "datasetName": self.dataset_name,
                 "presignedUrl": presignedUrl,
-            })
-        response = requests.request("POST", 
-                                    f"{self.base_url}/v1/llm/insert/trace", 
-                                    headers=headers, 
-                                    data=payload,
-                                    timeout=self.timeout)
-        
+            }
+        )
+        response = requests.request(
+            "POST",
+            f"{self.base_url}/v1/llm/insert/trace",
+            headers=headers,
+            data=payload,
+            timeout=self.timeout,
+        )
 
     def _upload_traces(self, save_json_to_pwd=None):
         """Save traces to a file"""
@@ -351,7 +355,7 @@ class LlamaIndexTracer:
         presignedUrl = self._get_presigned_url()
         self._put_presigned_url(presignedUrl, filename)
         self._insert_traces(presignedUrl)
-        print("Traces uplaoded")
+        print("Traces uploaded")
 
     def get_upload_status(self):
         """Check the status of the trace upload."""

{ragaai_catalyst-2.0.7.2b0 → ragaai_catalyst-2.0.7.2b1}/ragaai_catalyst/tracers/upload_traces.py

@@ -5,13 +5,15 @@ from datetime import datetime
 
 
 class UploadTraces:
-    def __init__(self, 
-                 json_file_path,
-                 project_name,
-                 project_id,
-                 dataset_name,
-                 user_detail,
-                 base_url):
+    def __init__(
+        self,
+        json_file_path,
+        project_name,
+        project_id,
+        dataset_name,
+        user_detail,
+        base_url,
+    ):
         self.json_file_path = json_file_path
         self.project_name = project_name
         self.project_id = project_id
@@ -25,31 +27,35 @@ class UploadTraces:
             "trace_id": {"columnType": "traceId"},
             "trace_uri": {"columnType": "traceUri"},
             "prompt": {"columnType": "prompt"},
-            "response":{"columnType": "response"},
+            "response": {"columnType": "response"},
             "context": {"columnType": "context"},
-            "llm_model": {"columnType":"pipeline"},
+            "llm_model": {"columnType": "pipeline"},
             "recorded_on": {"columnType": "metadata"},
-            "embed_model": {"columnType":"pipeline"},
+            "embed_model": {"columnType": "pipeline"},
             "log_source": {"columnType": "metadata"},
-            "vector_store":{"columnType":"pipeline"},
-            "feedback": {"columnType":"feedBack"}
+            "vector_store": {"columnType": "pipeline"},
+            "feedback": {"columnType": "feedBack"},
         }
+
         def make_request():
             headers = {
                 "Content-Type": "application/json",
                 "Authorization": f"Bearer {os.getenv('RAGAAI_CATALYST_TOKEN')}",
                 "X-Project-Name": self.project_name,
             }
-            payload = json.dumps({
-                "datasetName": self.dataset_name,
-                "schemaMapping": SCHEMA_MAPPING_NEW,
-                "traceFolderUrl": None,
-            })
-            response = requests.request("POST",
+            payload = json.dumps(
+                {
+                    "datasetName": self.dataset_name,
+                    "schemaMapping": SCHEMA_MAPPING_NEW,
+                    "traceFolderUrl": None,
+                }
+            )
+            response = requests.request(
+                "POST",
                 f"{self.base_url}/v1/llm/dataset/logs",
                 headers=headers,
                 data=payload,
-                timeout=self.timeout
+                timeout=self.timeout,
             )
 
             return response
@@ -64,64 +70,69 @@ class UploadTraces:
         return response.status_code
 
     def _get_presigned_url(self):
-        payload = json.dumps({
+        payload = json.dumps(
+            {
                 "datasetName": self.dataset_name,
                 "numFiles": 1,
-            })
+            }
+        )
         headers = {
             "Content-Type": "application/json",
             "Authorization": f"Bearer {os.getenv('RAGAAI_CATALYST_TOKEN')}",
             "X-Project-Name": self.project_name,
         }
 
-        response = requests.request("GET", 
-                                    f"{self.base_url}/v1/llm/presigned-url", 
-                                    headers=headers, 
-                                    data=payload,
-                                    timeout=self.timeout)
+        response = requests.request(
+            "GET",
+            f"{self.base_url}/v1/llm/presigned-url",
+            headers=headers,
+            data=payload,
+            timeout=self.timeout,
+        )
         if response.status_code == 200:
             presignedUrls = response.json()["data"]["presignedUrls"][0]
             return presignedUrls
 
     def _put_presigned_url(self, presignedUrl, filename):
         headers = {
-                "Content-Type": "application/json",
-            }
+            "Content-Type": "application/json",
+        }
 
         if "blob.core.windows.net" in presignedUrl:  # Azure
             headers["x-ms-blob-type"] = "BlockBlob"
         print(f"Uploading traces...")
         with open(filename) as f:
             payload = f.read().replace("\n", "").replace("\r", "").encode()
-            
 
-        response = requests.request("PUT", 
-                                    presignedUrl, 
-                                    headers=headers, 
-                                    data=payload,
-                                    timeout=self.timeout)
+        response = requests.request(
+            "PUT", presignedUrl, headers=headers, data=payload, timeout=self.timeout
+        )
         if response.status_code != 200 or response.status_code != 201:
             return response, response.status_code
 
     def _insert_traces(self, presignedUrl):
         headers = {
-                "Authorization": f"Bearer {os.getenv('RAGAAI_CATALYST_TOKEN')}",
-                "Content-Type": "application/json",
-                "X-Project-Name": self.project_name,
-            }
-        payload = json.dumps({
+            "Authorization": f"Bearer {os.getenv('RAGAAI_CATALYST_TOKEN')}",
+            "Content-Type": "application/json",
+            "X-Project-Name": self.project_name,
+        }
+        payload = json.dumps(
+            {
                 "datasetName": self.dataset_name,
                 "presignedUrl": presignedUrl,
-            })
-        response = requests.request("POST", 
-                                    f"{self.base_url}/v1/llm/insert/trace", 
-                                    headers=headers, 
-                                    data=payload,
-                                    timeout=self.timeout)
+            }
+        )
+        response = requests.request(
+            "POST",
+            f"{self.base_url}/v1/llm/insert/trace",
+            headers=headers,
+            data=payload,
+            timeout=self.timeout,
+        )
 
     def upload_traces(self):
         self._create_dataset_schema_with_trace()
         presignedUrl = self._get_presigned_url()
         self._put_presigned_url(presignedUrl, self.json_file_path)
         self._insert_traces(presignedUrl)
-        print("Traces uplaoded")
+        print("Traces uploaded")

{ragaai_catalyst-2.0.7.2b0 → ragaai_catalyst-2.0.7.2b1}/ragaai_catalyst.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ragaai_catalyst
-Version: 2.0.7.2b0
+Version: 2.0.7.2b1
 Summary: RAGA AI CATALYST
 Author-email: Kiran Scaria <kiran.scaria@raga.ai>, Kedar Gaikwad <kedar.gaikwad@raga.ai>, Dushyant Mahajan <dushyant.mahajan@raga.ai>, Siddhartha Kosti <siddhartha.kosti@raga.ai>, Ritika Goel <ritika.goel@raga.ai>, Vijay Chaurasia <vijay.chaurasia@raga.ai>
 Requires-Python: >=3.9