Menu
Guides the model on performing basic text generation, counting tokens, detokenizing lists, and generating structurally validated JSON outputs with LollmsClient.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | Lollms Text Generation |
| description | Guides the model on performing basic text generation, counting tokens, detokenizing lists, and generating structurally validated JSON outputs with LollmsClient. |
| author | ParisNeo |
| version | 1.0.0 |
| category | lollms_client/base |
| created | "2026-05-24T00:00:00.000Z" |
This skill teaches how to interact with the core LLM capabilities of the LollmsClient class. It covers basic generation, token management, and structured schema generation.
The client acts as the central interface for all interactions. It dynamically handles the loading of different local and remote binding backends.
from lollms_client import LollmsClient
client = LollmsClient(
llm_binding_name="ollama",
llm_binding_config={
"model_name": "gemma4:e2b",
"host_address": "http://localhost:11434"
},
user_name="ParisNeo",
ai_name="Lollms"
)
Perform simple completions using raw strings.
# Generate text directly
response = client.generate_text(
prompt="Why is Rust chosen for system-level programming?",
system_prompt="You are a senior software architect. Answer concisely.",
temperature=0.7,
n_predict=512
)
print(response)
Since different models have varying token behaviors, always use the client's tokenization APIs to safely calculate context footprints.
# Tokenize a string into token IDs
tokens = client.tokenize("systems programming")
# Detokenize token IDs back to a string
decoded_string = client.detokenize(tokens)
# Directly count tokens of a text string
token_count = client.count_tokens("systems programming")
print(f"Token count: {token_count}")
Generating unstructured text that needs to be parsed can be fragile. Use the generate_structured_content or generate_structured_content_pydantic methods to enforce schema validation at generation time.
# Generate structured outputs matching a Pydantic schema
from pydantic import BaseModel, Field
class APIEndpoint(BaseModel):
route: str = Field(description="The URL route path, e.g. /api/users")
method: str = Field(description="HTTP Method, e.g. GET, POST")
description: str = Field(description="A short explanation of what the route does")
api_schema = client.generate_structured_content(
prompt="Design a simple user registration endpoint",
schema=APIEndpoint,
temperature=0.1
)
print(api_schema)
# Output matches: {"route": "/api/register", "method": "POST", "description": "Registers a new user..."}
Teaches how to build, discover, and execute local, zero-configuration Python tools in Lollms using AST schema parsing and context injection. Includes step-by-step tool file construction guide and code examples.
Teaches the model about the persistent tiered memory system (Level 1 Working, Level 2 Deep, Level 3 Archive), proactive keyword pulling, and the required tagging protocols.
Teaches the model how to formulate strategic <coding_plan> blocks, apply indentation-agnostic Aider search/replace patches, manage Git-like version logs, and control in-message status reporting.
Teaches the model how to manage stateful discussions, track conversational trees/branches, navigate alternative sibling replies, and execute context-aware generation.
Teaches how to import, parse, and process PDF, DOCX, PPTX, and image files using anchor-mapped and OCR import modes in LollmsDiscussion.
Teaches how to coordinate multiple specialized agents, distribute tasks, establish consensus, and manage role-based multi-agent swarms using LollmsSwarm.