import-kb 0.1.0__tar.gz

import_kb-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Nebiyu Samuel
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

import_kb-0.1.0/PKG-INFO

@@ -0,0 +1,78 @@
+Metadata-Version: 2.4
+Name: import-kb
+Version: 0.1.0
+Summary: A package for importing knowledge and embedding text.
+Author-email: Coderskin <your.email@example.com>
+License: MIT
+Keywords: knowledge,embedding,openai,chromadb
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai>=0.27.0
+Requires-Dist: chromadb>=0.3.21
+Requires-Dist: python-dotenv>=0.20.0
+Provides-Extra: dev
+Requires-Dist: pytest>=6.2.5; extra == "dev"
+Dynamic: license-file
+
+# import-knowledge-package/import-knowledge-package/README.md
+
+# Import Knowledge Package
+
+This project provides a Python package for importing and processing knowledge from specified JSONL and curriculum files. It utilizes OpenAI's embedding model to generate embeddings for the knowledge data, which can then be stored in a Chroma database for later retrieval and use.
+
+## Project Structure
+
+```
+import-knowledge-package
+├── KB
+│   ├── curriculum.metta
+│   ├── max_distilled_knowledge.jsonl
+│   └── oma_distilled_knowledge.jsonl
+├── src
+│   └── import_knowledge
+│       ├── __init__.py
+│       └── import_knowledge.py
+├── pyproject.toml
+├── setup.py
+├── MANIFEST.in
+└── README.md
+```
+
+### KB Directory
+
+- **curriculum.metta**: Contains the curriculum data used for knowledge transfer.
+- **max_distilled_knowledge.jsonl**: Contains distilled knowledge data related to "max".
+- **oma_distilled_knowledge.jsonl**: Contains distilled knowledge data related to "oma".
+
+### Source Directory
+
+- **import_knowledge/__init__.py**: Marks the directory as a Python package.
+- **import_knowledge.py**: Contains the main logic for importing knowledge, including functions for embedding text and processing knowledge files.
+
+## Installation
+
+To install the package, clone the repository and run:
+
+```bash
+pip install .
+```
+
+## Usage
+
+After installation, you can use the package to import knowledge by running the `import_knowledge.py` script. Ensure that your environment is set up with the necessary API keys and dependencies.
+
+## Dependencies
+
+- OpenAI API
+- ChromaDB
+- dotenv
+
+Make sure to install the required dependencies listed in `setup.py` or `pyproject.toml`.
+
+## License
+
+This project is licensed under the MIT License. See the LICENSE file for more details.

import_kb-0.1.0/README.md

@@ -0,0 +1,58 @@
+# import-knowledge-package/import-knowledge-package/README.md
+
+# Import Knowledge Package
+
+This project provides a Python package for importing and processing knowledge from specified JSONL and curriculum files. It utilizes OpenAI's embedding model to generate embeddings for the knowledge data, which can then be stored in a Chroma database for later retrieval and use.
+
+## Project Structure
+
+```
+import-knowledge-package
+├── KB
+│   ├── curriculum.metta
+│   ├── max_distilled_knowledge.jsonl
+│   └── oma_distilled_knowledge.jsonl
+├── src
+│   └── import_knowledge
+│       ├── __init__.py
+│       └── import_knowledge.py
+├── pyproject.toml
+├── setup.py
+├── MANIFEST.in
+└── README.md
+```
+
+### KB Directory
+
+- **curriculum.metta**: Contains the curriculum data used for knowledge transfer.
+- **max_distilled_knowledge.jsonl**: Contains distilled knowledge data related to "max".
+- **oma_distilled_knowledge.jsonl**: Contains distilled knowledge data related to "oma".
+
+### Source Directory
+
+- **import_knowledge/__init__.py**: Marks the directory as a Python package.
+- **import_knowledge.py**: Contains the main logic for importing knowledge, including functions for embedding text and processing knowledge files.
+
+## Installation
+
+To install the package, clone the repository and run:
+
+```bash
+pip install .
+```
+
+## Usage
+
+After installation, you can use the package to import knowledge by running the `import_knowledge.py` script. Ensure that your environment is set up with the necessary API keys and dependencies.
+
+## Dependencies
+
+- OpenAI API
+- ChromaDB
+- dotenv
+
+Make sure to install the required dependencies listed in `setup.py` or `pyproject.toml`.
+
+## License
+
+This project is licensed under the MIT License. See the LICENSE file for more details.

import_kb-0.1.0/pyproject.toml

@@ -0,0 +1,42 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "import-kb"
+version = "0.1.0"
+description = "A package for importing knowledge and embedding text."
+readme = "README.md"
+authors = [
+    { name = "Coderskin", email = "your.email@example.com" }
+]
+license = { text = "MIT" }
+keywords = ["knowledge", "embedding", "openai", "chromadb"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+requires-python = ">=3.7"
+dependencies = [
+    "openai>=0.27.0",
+    "chromadb>=0.3.21",
+    "python-dotenv>=0.20.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=6.2.5",
+]
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+import_knowledge = ["KB/*.jsonl", "KB/*.metta"]
+
+[project.scripts]
+import-knowledge = "import_knowledge.import_knowledge:main"

import_kb-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

import_kb-0.1.0/src/import_kb.egg-info/PKG-INFO

@@ -0,0 +1,78 @@
+Metadata-Version: 2.4
+Name: import-kb
+Version: 0.1.0
+Summary: A package for importing knowledge and embedding text.
+Author-email: Coderskin <your.email@example.com>
+License: MIT
+Keywords: knowledge,embedding,openai,chromadb
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai>=0.27.0
+Requires-Dist: chromadb>=0.3.21
+Requires-Dist: python-dotenv>=0.20.0
+Provides-Extra: dev
+Requires-Dist: pytest>=6.2.5; extra == "dev"
+Dynamic: license-file
+
+# import-knowledge-package/import-knowledge-package/README.md
+
+# Import Knowledge Package
+
+This project provides a Python package for importing and processing knowledge from specified JSONL and curriculum files. It utilizes OpenAI's embedding model to generate embeddings for the knowledge data, which can then be stored in a Chroma database for later retrieval and use.
+
+## Project Structure
+
+```
+import-knowledge-package
+├── KB
+│   ├── curriculum.metta
+│   ├── max_distilled_knowledge.jsonl
+│   └── oma_distilled_knowledge.jsonl
+├── src
+│   └── import_knowledge
+│       ├── __init__.py
+│       └── import_knowledge.py
+├── pyproject.toml
+├── setup.py
+├── MANIFEST.in
+└── README.md
+```
+
+### KB Directory
+
+- **curriculum.metta**: Contains the curriculum data used for knowledge transfer.
+- **max_distilled_knowledge.jsonl**: Contains distilled knowledge data related to "max".
+- **oma_distilled_knowledge.jsonl**: Contains distilled knowledge data related to "oma".
+
+### Source Directory
+
+- **import_knowledge/__init__.py**: Marks the directory as a Python package.
+- **import_knowledge.py**: Contains the main logic for importing knowledge, including functions for embedding text and processing knowledge files.
+
+## Installation
+
+To install the package, clone the repository and run:
+
+```bash
+pip install .
+```
+
+## Usage
+
+After installation, you can use the package to import knowledge by running the `import_knowledge.py` script. Ensure that your environment is set up with the necessary API keys and dependencies.
+
+## Dependencies
+
+- OpenAI API
+- ChromaDB
+- dotenv
+
+Make sure to install the required dependencies listed in `setup.py` or `pyproject.toml`.
+
+## License
+
+This project is licensed under the MIT License. See the LICENSE file for more details.

import_kb-0.1.0/src/import_kb.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+LICENSE
+README.md
+pyproject.toml
+src/import_kb.egg-info/PKG-INFO
+src/import_kb.egg-info/SOURCES.txt
+src/import_kb.egg-info/dependency_links.txt
+src/import_kb.egg-info/entry_points.txt
+src/import_kb.egg-info/requires.txt
+src/import_kb.egg-info/top_level.txt
+src/import_knowledge/__init__.py
+src/import_knowledge/import_knowledge.py
+src/import_knowledge/KB/curriculum.metta
+src/import_knowledge/KB/max_distilled_knowledge.jsonl
+src/import_knowledge/KB/oma_distilled_knowledge.jsonl

import_kb-0.1.0/src/import_kb.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

import_kb-0.1.0/src/import_kb.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+import-knowledge = import_knowledge.import_knowledge:main

import_kb-0.1.0/src/import_kb.egg-info/requires.txt

@@ -0,0 +1,6 @@
+openai>=0.27.0
+chromadb>=0.3.21
+python-dotenv>=0.20.0
+
+[dev]
+pytest>=6.2.5

import_kb-0.1.0/src/import_kb.egg-info/top_level.txt

@@ -0,0 +1 @@
+import_knowledge

import_kb-0.1.0/src/import_knowledge/KB/curriculum.metta

@@ -0,0 +1,2 @@
+# FILE: /import-knowledge-package/import-knowledge-package/KB/curriculum.metta
+# This file is intentionally left blank.

import_kb-0.1.0/src/import_knowledge/KB/max_distilled_knowledge.jsonl

@@ -0,0 +1,27 @@
+{
+    "id": "max_knowledge_001",
+    "document": "Max is known for his exceptional problem-solving skills and creativity. He often approaches challenges with a unique perspective, leading to innovative solutions.",
+    "metadata": {
+        "domain": "personal_development",
+        "type": "fact",
+        "tags": ["creativity", "problem-solving", "innovation"]
+    }
+}
+{
+    "id": "max_knowledge_002",
+    "document": "Max has a strong background in software development, particularly in Python and JavaScript. He has contributed to several open-source projects.",
+    "metadata": {
+        "domain": "technical_skills",
+        "type": "fact",
+        "tags": ["software development", "open-source", "Python", "JavaScript"]
+    }
+}
+{
+    "id": "max_knowledge_003",
+    "document": "Max enjoys collaborating with others and often takes on leadership roles in team projects. His communication skills are highly regarded.",
+    "metadata": {
+        "domain": "teamwork",
+        "type": "fact",
+        "tags": ["leadership", "communication", "collaboration"]
+    }
+}

import_kb-0.1.0/src/import_knowledge/KB/oma_distilled_knowledge.jsonl

@@ -0,0 +1,27 @@
+{
+    "id": "oma_001",
+    "document": "Oma is a term used to refer to a grandmother in various cultures, often associated with wisdom and nurturing.",
+    "metadata": {
+        "domain": "family",
+        "type": "fact",
+        "tags": ["family", "grandmother", "wisdom"]
+    }
+}
+{
+    "id": "oma_002",
+    "document": "In many cultures, oma is a central figure in family gatherings, often sharing stories and traditions.",
+    "metadata": {
+        "domain": "family",
+        "type": "fact",
+        "tags": ["family", "tradition", "storytelling"]
+    }
+}
+{
+    "id": "oma_003",
+    "document": "The role of an oma can vary significantly between cultures, influencing family dynamics and values.",
+    "metadata": {
+        "domain": "cultural studies",
+        "type": "fact",
+        "tags": ["culture", "family dynamics", "values"]
+    }
+}

import_kb-0.1.0/src/import_knowledge/__init__.py

@@ -0,0 +1,2 @@
+# filepath: /import-knowledge-package/import-knowledge-package/src/import_knowledge/__init__.py
+"""This package provides functionality for importing knowledge from various sources."""

import_kb-0.1.0/src/import_knowledge/import_knowledge.py

@@ -0,0 +1,152 @@
+import os
+import json
+from pathlib import Path
+import chromadb
+import openai
+from dotenv import load_dotenv
+
+# Load API Key from .env
+load_dotenv()
+
+# Look for the DB path
+_PACKAGE_DIR = os.path.dirname(os.path.abspath(__file__))
+
+# --- Configuration ---
+EMBEDDING_MODEL = "text-embedding-3-large"
+COLLECTION_NAME = "memories"
+KNOWLEDGE_FILES = [
+    os.path.join(_PACKAGE_DIR, "KB", "oma_distilled_knowledge.jsonl"),
+    os.path.join(_PACKAGE_DIR, "KB", "max_distilled_knowledge.jsonl")
+]
+CURRICULUM_FILE = os.path.join(_PACKAGE_DIR, "KB", "curriculum.metta")
+
+DB_PATH = os.environ.get(
+    "CHROMA_DB_PATH",
+    "/PeTTa/chroma_db" if os.path.isdir("/PeTTa/chroma_db") else
+    os.path.join(_PACKAGE_DIR, "..", "..", "chroma_db")
+)
+
+# --- Embedding Function  ---
+def _embed_batch(texts):
+    """Embed a list of texts via OpenAI. Returns list of float vectors."""
+    client = openai.OpenAI()
+    resp = client.embeddings.create(model=EMBEDDING_MODEL, input=texts)
+    return [item.embedding for item in resp.data]
+
+def main():
+    has_any_knowledge = any(Path(f).exists() for f in KNOWLEDGE_FILES)
+    if not has_any_knowledge and not Path(CURRICULUM_FILE).exists():
+        print("Error: Neither knowledge nor curriculum files were found.")
+        return
+
+    print(f"Connecting to Agent LTM at: {DB_PATH}")
+    os.makedirs(DB_PATH, exist_ok=True)
+    client = chromadb.PersistentClient(path=DB_PATH)
+    
+    collection = client.get_or_create_collection(
+        name=COLLECTION_NAME,
+        embedding_function=None,
+    )
+
+    ids = []
+    documents = []
+    metadatas = []
+    seen_ids = set()
+
+    for k_file in KNOWLEDGE_FILES:
+        if Path(k_file).exists():
+            print(f"Loading distilled knowledge from {k_file}...")
+            with open(k_file, "r", encoding="utf-8") as f:
+                for line in f:
+                    if not line.strip():
+                        continue
+                    
+                    record = json.loads(line)
+                    record_id = record["id"]
+                    
+                    if record_id in seen_ids:
+                        continue
+                        
+                    seen_ids.add(record_id)
+                    ids.append(record_id)
+                    documents.append(record["document"])
+
+                    
+                    meta = record.get("metadata", {})
+                    clean_meta = {
+                        "source": "distilled_memory",
+                        "breadcrumb": f"LTM > {meta.get('domain', 'general')} > {meta.get('type', 'fact')}",
+                        "type": "chunk",
+                        "time": "knowledge_prior"
+                    }
+                    
+                    for k, v in meta.items():
+                        if isinstance(v, list):
+                            clean_meta[k] = " | ".join(v) if v else "None"
+                        else:
+                            clean_meta[k] = v
+                    
+                    metadatas.append(clean_meta)
+        else:
+            print(f"Warning: {k_file} not found. Skipping...")
+
+    if Path(CURRICULUM_FILE).exists():
+        print("Loading curriculum...")
+        with open(CURRICULUM_FILE, "r", encoding="utf-8") as f:
+            content = f.read()
+            chunks = [chunk.strip() for chunk in content.split("\n\n") if chunk.strip()]
+            
+            for idx, chunk in enumerate(chunks):
+                curriculum_id = f"curriculum_mem_{idx}"
+                
+                if curriculum_id in seen_ids:
+                    continue
+                    
+                seen_ids.add(curriculum_id)
+                ids.append(curriculum_id)
+                documents.append(chunk)
+                metadatas.append({
+                    "source": "curriculum",
+                    "breadcrumb": "LTM > curriculum",
+                    "type": "chunk",
+                    "time": "knowledge_prior"
+                })
+    else:
+        print(f"Warning: {CURRICULUM_FILE} not found. Skipping...")
+
+
+
+    count = len(ids)
+    if count == 0:
+        print("No documents to process.")
+        return
+
+    print(f"Generating OpenAI '{EMBEDDING_MODEL}' embeddings for {count} records. Please wait...")
+
+    batch_size = 100
+    for i in range(0, count, batch_size):
+        end = min(i + batch_size, count)
+        
+        batch_docs = documents[i:end]
+        
+        # Manually compute the embeddings via OpenAI API to match the agent's expected vector lengths
+        try:
+            batch_embeddings = _embed_batch(batch_docs)
+        except Exception as e:
+            print(f"Fatal error generating embeddings: {e}")
+            return
+        
+        # Use upside instead of add to gracefully handle re-runs
+        collection.upsert(
+            ids=ids[i:end],
+            embeddings=batch_embeddings,
+            documents=batch_docs,
+            metadatas=metadatas[i:end]
+        )
+        print(f"  -> Embedded and upserted batch {i} to {end}")
+
+    print("\nKnowledge Transfer Complete!")
+    print(f"New Agent Database now has {collection.count()} total memories.")
+
+if __name__ == "__main__":
+    main()