agno 2.0.4__py3-none-any.whl → 2.0.6__py3-none-any.whl

agno/vectordb/chroma/chromadb.py

@@ -1,4 +1,5 @@
 import asyncio
+import json
 from hashlib import md5
 from typing import Any, Dict, List, Mapping, Optional, Union, cast
 
@@ -60,6 +61,44 @@ class ChromaDb(VectorDb):
         # Chroma client kwargs
         self.kwargs = kwargs
 
+    def _flatten_metadata(self, metadata: Dict[str, Any]) -> Dict[str, Union[str, int, float, bool]]:
+        """
+        Flatten nested metadata to ChromaDB-compatible format.
+
+        Args:
+            metadata: Dictionary that may contain nested structures
+
+        Returns:
+            Flattened dictionary with only primitive values
+        """
+        flattened: Dict[str, Any] = {}
+
+        def _flatten_recursive(obj: Any, prefix: str = "") -> None:
+            if isinstance(obj, dict):
+                if len(obj) == 0:
+                    # Handle empty dictionaries by converting to JSON string
+                    flattened[prefix] = json.dumps(obj)
+                else:
+                    for key, value in obj.items():
+                        new_key = f"{prefix}.{key}" if prefix else key
+                        _flatten_recursive(value, new_key)
+            elif isinstance(obj, (list, tuple)):
+                # Convert lists/tuples to JSON strings
+                flattened[prefix] = json.dumps(obj)
+            elif isinstance(obj, (str, int, float, bool)) or obj is None:
+                if obj is not None:  # ChromaDB doesn't accept None values
+                    flattened[prefix] = obj
+            else:
+                # Convert other complex types to JSON strings
+                try:
+                    flattened[prefix] = json.dumps(obj)
+                except (TypeError, ValueError):
+                    # If it can't be serialized, convert to string
+                    flattened[prefix] = str(obj)
+
+        _flatten_recursive(metadata)
+        return flattened
+
     @property
     def client(self) -> ClientAPI:
         if self._client is None:
@@ -147,11 +186,14 @@ class ChromaDb(VectorDb):
 
             metadata["content_hash"] = content_hash
 
+            # Flatten metadata for ChromaDB compatibility
+            flattened_metadata = self._flatten_metadata(metadata)
+
             docs_embeddings.append(document.embedding)
             docs.append(cleaned_content)
             ids.append(doc_id)
-            docs_metadata.append(metadata)
-            log_debug(f"Prepared document: {document.id} | {document.name} | {metadata}")
+            docs_metadata.append(flattened_metadata)
+            log_debug(f"Prepared document: {document.id} | {document.name} | {flattened_metadata}")
 
         if self._collection is None:
             logger.warning("Collection does not exist")
@@ -196,11 +238,14 @@ class ChromaDb(VectorDb):
 
             metadata["content_hash"] = content_hash
 
+            # Flatten metadata for ChromaDB compatibility
+            flattened_metadata = self._flatten_metadata(metadata)
+
             docs_embeddings.append(document.embedding)
             docs.append(cleaned_content)
             ids.append(doc_id)
-            docs_metadata.append(metadata)
-            log_debug(f"Prepared document: {document.id} | {document.name} | {metadata}")
+            docs_metadata.append(flattened_metadata)
+            log_debug(f"Prepared document: {document.id} | {document.name} | {flattened_metadata}")
 
         if self._collection is None:
             logger.warning("Collection does not exist")
@@ -262,11 +307,14 @@ class ChromaDb(VectorDb):
 
             metadata["content_hash"] = content_hash
 
+            # Flatten metadata for ChromaDB compatibility
+            flattened_metadata = self._flatten_metadata(metadata)
+
             docs_embeddings.append(document.embedding)
             docs.append(cleaned_content)
             ids.append(doc_id)
-            docs_metadata.append(metadata)
-            log_debug(f"Upserted document: {document.id} | {document.name} | {metadata}")
+            docs_metadata.append(flattened_metadata)
+            log_debug(f"Upserted document: {document.id} | {document.name} | {flattened_metadata}")
 
         if self._collection is None:
             logger.warning("Collection does not exist")
@@ -313,11 +361,14 @@ class ChromaDb(VectorDb):
 
             metadata["content_hash"] = content_hash
 
+            # Flatten metadata for ChromaDB compatibility
+            flattened_metadata = self._flatten_metadata(metadata)
+
             docs_embeddings.append(document.embedding)
             docs.append(cleaned_content)
             ids.append(doc_id)
-            docs_metadata.append(metadata)
-            log_debug(f"Upserted document: {document.id} | {document.name} | {metadata}")
+            docs_metadata.append(flattened_metadata)
+            log_debug(f"Upserted document: {document.id} | {document.name} | {flattened_metadata}")
 
         if self._collection is None:
             logger.warning("Collection does not exist")
@@ -747,6 +798,9 @@ class ChromaDb(VectorDb):
                     logger.debug(f"No documents found with content_id: {content_id}")
                     return
 
+                # Flatten the new metadata first
+                flattened_new_metadata = self._flatten_metadata(metadata)
+
                 # Merge metadata for each document
                 updated_metadatas = []
                 for i, current_meta in enumerate(current_metadatas or []):
@@ -754,26 +808,13 @@ class ChromaDb(VectorDb):
                         meta_dict: Dict[str, Any] = {}
                     else:
                         meta_dict = dict(current_meta)  # Convert Mapping to dict
-                    updated_meta: Dict[str, Any] = meta_dict.copy()
-                    updated_meta.update(metadata)
-
-                    if "filters" not in updated_meta:
-                        updated_meta["filters"] = {}
-                    if isinstance(updated_meta["filters"], dict):
-                        updated_meta["filters"].update(metadata)
-                    else:
-                        updated_meta["filters"] = metadata
-                    updated_metadatas.append(updated_meta)
 
-                # Update the documents
-                # Filter out None values from metadata as ChromaDB doesn't accept them
-                cleaned_metadatas = []
-                for meta in updated_metadatas:
-                    cleaned_meta = {k: v for k, v in meta.items() if v is not None}
-                    cleaned_metadatas.append(cleaned_meta)
+                    # Update with flattened metadata
+                    meta_dict.update(flattened_new_metadata)
+                    updated_metadatas.append(meta_dict)
 
                 # Convert to the expected type for ChromaDB
-                chroma_metadatas = cast(List[Mapping[str, Union[str, int, float, bool]]], cleaned_metadatas)
+                chroma_metadatas = cast(List[Mapping[str, Union[str, int, float, bool]]], updated_metadatas)
                 collection.update(ids=ids, metadatas=chroma_metadatas)  # type: ignore
                 logger.debug(f"Updated metadata for {len(ids)} documents with content_id: {content_id}")
 

agno/vectordb/lancedb/lance_db.py

@@ -950,17 +950,28 @@ class LanceDb(VectorDb):
                 logger.error("Table not initialized")
                 return
 
-            # Search for documents with the given content_id
-            query_filter = f"payload->>'content_id' = '{content_id}'"
-            results = self.table.search().where(query_filter).to_pandas()
+            # Get all documents and filter in Python (LanceDB doesn't support JSON operators)
+            total_count = self.table.count_rows()
+            results = self.table.search().select(["id", "payload"]).limit(total_count).to_pandas()
 
             if results.empty:
+                logger.debug("No documents found")
+                return
+
+            # Find matching documents with the given content_id
+            matching_rows = []
+            for _, row in results.iterrows():
+                payload = json.loads(row["payload"])
+                if payload.get("content_id") == content_id:
+                    matching_rows.append(row)
+
+            if not matching_rows:
                 logger.debug(f"No documents found with content_id: {content_id}")
                 return
 
             # Update each matching document
             updated_count = 0
-            for _, row in results.iterrows():
+            for row in matching_rows:
                 row_id = row["id"]
                 current_payload = json.loads(row["payload"])
 

agno/vectordb/milvus/milvus.py

@@ -423,6 +423,9 @@ class Milvus(VectorDb):
         else:
             for document in documents:
                 document.embed(embedder=self.embedder)
+                if not document.embedding:
+                    log_debug(f"Skipping document without embedding: {document.name} ({document.meta_data})")
+                    continue
                 cleaned_content = document.content.replace("\x00", "\ufffd")
                 doc_id = md5(cleaned_content.encode()).hexdigest()
 
@@ -465,6 +468,9 @@ class Milvus(VectorDb):
 
             async def process_document(document):
                 document.embed(embedder=self.embedder)
+                if not document.embedding:
+                    log_debug(f"Skipping document without embedding: {document.name} ({document.meta_data})")
+                    return None
                 cleaned_content = document.content.replace("\x00", "\ufffd")
                 doc_id = md5(cleaned_content.encode()).hexdigest()
 

agno/workflow/step.py

@@ -499,7 +499,7 @@ class Step:
                         if store_executor_outputs and workflow_run_response is not None:
                             self._store_executor_response(workflow_run_response, active_executor_run_response)  # type: ignore
 
-                        final_response = self._process_step_output(active_executor_run_response)  # type: ignore
+                        final_response = active_executor_run_response  # type: ignore
 
                     else:
                         raise ValueError(f"Unsupported executor type: {self._executor_type}")
@@ -513,6 +513,7 @@ class Step:
                 use_workflow_logger()
 
                 # Yield the step output
+                final_response = self._process_step_output(final_response)
                 yield final_response
 
                 # Emit StepCompletedEvent
@@ -865,7 +866,6 @@ class Step:
 
                         active_executor_run_response = None
                         async for event in response_stream:
-                            log_debug(f"Received async event from agent: {type(event).__name__}")
                             if isinstance(event, RunOutput) or isinstance(event, TeamRunOutput):
                                 active_executor_run_response = event
                                 break
@@ -877,7 +877,7 @@ class Step:
                         if store_executor_outputs and workflow_run_response is not None:
                             self._store_executor_response(workflow_run_response, active_executor_run_response)  # type: ignore
 
-                        final_response = self._process_step_output(active_executor_run_response)  # type: ignore
+                        final_response = active_executor_run_response  # type: ignore
                     else:
                         raise ValueError(f"Unsupported executor type: {self._executor_type}")
 
@@ -889,6 +889,7 @@ class Step:
                 use_workflow_logger()
 
                 # Yield the final response
+                final_response = self._process_step_output(final_response)
                 yield final_response
 
                 if stream_intermediate_steps and workflow_run_response:

agno/workflow/workflow.py

@@ -1708,6 +1708,7 @@ class Workflow:
         # Create workflow run response with PENDING status
         workflow_run_response = WorkflowRunOutput(
             run_id=run_id,
+            input=input,
             session_id=session_id,
             workflow_id=self.id,
             workflow_name=self.name,
@@ -1798,6 +1799,7 @@ class Workflow:
         # Create workflow run response with PENDING status
         workflow_run_response = WorkflowRunOutput(
             run_id=run_id,
+            input=input,
             session_id=session_id,
             workflow_id=self.id,
             workflow_name=self.name,
@@ -1971,6 +1973,7 @@ class Workflow:
         # Create workflow run response that will be updated by reference
         workflow_run_response = WorkflowRunOutput(
             run_id=run_id,
+            input=input,
             session_id=session_id,
             workflow_id=self.id,
             workflow_name=self.name,
@@ -2139,6 +2142,7 @@ class Workflow:
         # Create workflow run response that will be updated by reference
         workflow_run_response = WorkflowRunOutput(
             run_id=run_id,
+            input=input,
             session_id=session_id,
             workflow_id=self.id,
             workflow_name=self.name,

{agno-2.0.4.dist-info → agno-2.0.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agno
-Version: 2.0.4
+Version: 2.0.6
 Summary: Agno: a lightweight library for building Multi-Agent Systems
 Author-email: Ashpreet Bedi <ashpreet@agno.com>
 Project-URL: homepage, https://agno.com
@@ -161,6 +161,8 @@ Requires-Dist: opencv-python; extra == "opencv"
 Provides-Extra: psycopg
 Requires-Dist: psycopg-binary; extra == "psycopg"
 Requires-Dist: psycopg; extra == "psycopg"
+Provides-Extra: reportlab
+Requires-Dist: reportlab; extra == "reportlab"
 Provides-Extra: todoist
 Requires-Dist: todoist-api-python; extra == "todoist"
 Provides-Extra: valyu
@@ -306,6 +308,7 @@ Requires-Dist: agno[mem0]; extra == "tools"
 Requires-Dist: agno[memori]; extra == "tools"
 Requires-Dist: agno[google_bigquery]; extra == "tools"
 Requires-Dist: agno[psycopg]; extra == "tools"
+Requires-Dist: agno[reportlab]; extra == "tools"
 Requires-Dist: agno[trafilatura]; extra == "tools"
 Requires-Dist: agno[neo4j]; extra == "tools"
 Provides-Extra: storage
@@ -366,6 +369,7 @@ Dynamic: license-file
 <div align="center">
   <a href="https://docs.agno.com">📚 Documentation</a> &nbsp;|&nbsp;
   <a href="https://docs.agno.com/examples/introduction">💡 Examples</a> &nbsp;|&nbsp;
+  <a href="https://www.agno.com/?utm_source=github&utm_medium=readme&utm_campaign=agno-github&utm_content=header">🏠 Website</a> &nbsp;|&nbsp;
   <a href="https://github.com/agno-agi/agno/stargazers">🌟 Star Us</a>
 </div>
 
@@ -406,14 +410,14 @@ If you're new to Agno, follow our [quickstart](https://docs.agno.com/introductio
 
 After that, checkout the [examples gallery](https://docs.agno.com/examples/introduction) and build real-world applications with Agno.
 
-## Documentation, Community & More examples
+## Documentation, Community & More Examples
 
 - Docs: <a href="https://docs.agno.com" target="_blank" rel="noopener noreferrer">docs.agno.com</a>
 - Cookbook: <a href="https://github.com/agno-agi/agno/tree/main/cookbook" target="_blank" rel="noopener noreferrer">Cookbook</a>
 - Community forum: <a href="https://community.agno.com/" target="_blank" rel="noopener noreferrer">community.agno.com</a>
 - Discord: <a href="https://discord.gg/4MtYHHrgA8" target="_blank" rel="noopener noreferrer">discord</a>
 
-## Setup your coding agent to use Agno
+## Setup Your Coding Agent to Use Agno
 
 For LLMs and AI assistants to understand and navigate Agno's documentation, we provide an [llms.txt](https://docs.agno.com/llms.txt) or [llms-full.txt](https://docs.agno.com/llms-full.txt) file.
 
@@ -441,7 +445,7 @@ At Agno, we're obsessed with performance. Why? because even simple AI workflows
 
 While an Agent's run-time is bottlenecked by inference, we must do everything possible to minimize execution time, reduce memory usage, and parallelize tool calls. These numbers may seem trivial at first, but our experience shows that they add up even at a reasonably small scale.
 
-### Instantiation time
+### Instantiation Time
 
 Let's measure the time it takes for an Agent with 1 tool to start up. We'll run the evaluation 1000 times to get a baseline measurement.
 
@@ -469,7 +473,7 @@ Agno is on the left, notice how it finishes before LangGraph gets 1/2 way throug
 
 https://github.com/user-attachments/assets/ba466d45-75dd-45ac-917b-0a56c5742e23
 
-### Memory usage
+### Memory Usage
 
 To measure memory usage, we use the `tracemalloc` library. We first calculate a baseline memory usage by running an empty function, then run the Agent 1000x times and calculate the difference. This gives a (reasonably) isolated measurement of the memory usage of the Agent.