chore: (docs) Reconcile new SDK conventions in docs (#355)
This commit is contained in:
Vineeth Voruganti
GitHub
parent
4add711711
commit
4fcf6c4574
|
|
@ -15,11 +15,11 @@ Assuming reasoning is enabled, you can control the perspectives representations
|
|||
|
||||
When `observe_me=true` (the default), Honcho forms one representation per peer, reasoning over every message written to that peer across all sessions.
|
||||
|
||||
You can retrieve a subset of conclusions from a peer's representation using `get_representation()`:
|
||||
You can retrieve a subset of conclusions from a peer's representation using `representation()`:
|
||||
|
||||
```python
|
||||
# Retrieve conclusions from Honcho's representation of Alice (across all sessions)
|
||||
alice_rep = session.get_representation("alice")
|
||||
alice_rep = session.representation("alice")
|
||||
|
||||
# Or via chat
|
||||
response = alice.chat("What are Alice's main interests?", session_id=session.id)
|
||||
|
|
@ -93,7 +93,7 @@ charlie = honcho.peer("charlie")
|
|||
session.add_peers([alice, bob, charlie])
|
||||
|
||||
# Enable Alice to form representations of others
|
||||
session.set_peer_config(alice, SessionPeerConfig(observe_others=True))
|
||||
session.set_peer_configuration(alice, SessionPeerConfig(observe_others=True))
|
||||
|
||||
# Add messages
|
||||
session.add_messages([
|
||||
|
|
@ -111,9 +111,9 @@ session2.add_messages([
|
|||
])
|
||||
|
||||
# Retrieve conclusions from different perspectives
|
||||
honcho_view = session.get_representation("alice") # Across all sessions
|
||||
bob_view = session.get_representation("alice", target="bob") # Alice's view of Bob
|
||||
charlie_view = session2.get_representation("alice", target="charlie") # Alice's view of Charlie
|
||||
honcho_view = session.representation("alice") # Across all sessions
|
||||
bob_view = session.representation("alice", target="bob") # Alice's view of Bob
|
||||
charlie_view = session2.representation("alice", target="charlie") # Alice's view of Charlie
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
|
|
@ -128,7 +128,7 @@ const charlie = await honcho.peer("charlie");
|
|||
|
||||
await session.addPeers([alice, bob, charlie]);
|
||||
|
||||
await session.setPeerConfig(alice, { observeOthers: true });
|
||||
await session.setPeerConfiguration(alice, { observeOthers: true });
|
||||
|
||||
await session.addMessages([
|
||||
bob.message("I had pancakes for breakfast."),
|
||||
|
|
@ -144,9 +144,9 @@ await session2.addMessages([
|
|||
]);
|
||||
|
||||
// Retrieve conclusions from different perspectives
|
||||
const honchoView = await session.getRepresentation("alice"); // Across all sessions
|
||||
const bobView = await session.getRepresentation("alice", { target: "bob" }); // Alice's view of Bob
|
||||
const charlieView = await session2.getRepresentation("alice", { target: "charlie" }); // Alice's view of Charlie
|
||||
const honchoView = await session.representation("alice"); // Across all sessions
|
||||
const bobView = await session.representation("alice", { target: "bob" }); // Alice's view of Bob
|
||||
const charlieView = await session2.representation("alice", { target: "charlie" }); // Alice's view of Charlie
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
|
|
@ -224,7 +224,7 @@ This architecture enables:
|
|||
|
||||
## Semantic Search Parameters
|
||||
|
||||
Both `get_representation()` and `chat()` support semantic filtering to retrieve a subset of relevant conclusions. You can optionally filter by session to retrieve only conclusions from specific session context:
|
||||
Both `representation()` and `chat()` support semantic filtering to retrieve a subset of relevant conclusions. You can optionally filter by session to retrieve only conclusions from specific session context:
|
||||
|
||||
| Parameter | Type | Description |
|
||||
|-----------|------|-------------|
|
||||
|
|
@ -237,7 +237,7 @@ Both `get_representation()` and `chat()` support semantic filtering to retrieve
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Retrieve conclusions about billing from Alice's representation of Bob
|
||||
alice_view_billing = session.get_representation(
|
||||
alice_view_billing = session.representation(
|
||||
"alice",
|
||||
target="bob",
|
||||
search_query="billing issues",
|
||||
|
|
@ -247,7 +247,7 @@ alice_view_billing = session.get_representation(
|
|||
```
|
||||
|
||||
```typescript TypeScript
|
||||
const aliceViewBilling = await session.getRepresentation("alice", {
|
||||
const aliceViewBilling = await session.representation("alice", {
|
||||
target: "bob",
|
||||
searchQuery: "billing issues",
|
||||
searchTopK: 10,
|
||||
|
|
@ -267,5 +267,5 @@ Directional representations update automatically through the reasoning pipeline
|
|||
The pipeline respects scoping—Honcho's representations reason over messages across all sessions, while directional representations only reason over messages from sessions where the observer was an active participant.
|
||||
|
||||
<Note>
|
||||
Conclusions are cached for fast retrieval. Use `get_representation()` to retrieve stored conclusions for dashboards and analytics. Use `peer.chat()` when you need query-specific reasoning with natural language.
|
||||
Conclusions are cached for fast retrieval. Use `representation()` to retrieve stored conclusions for dashboards and analytics. Use `peer.chat()` when you need query-specific reasoning with natural language.
|
||||
</Note>
|
||||
|
|
|
|||
|
|
@ -22,15 +22,15 @@ from honcho import Honcho
|
|||
honcho = Honcho()
|
||||
|
||||
# Simple peer filter
|
||||
peers = honcho.get_peers(filters={"peer_id": "alice"})
|
||||
peers = honcho.peers(filters={"peer_id": "alice"})
|
||||
|
||||
# Simple session filter with metadata
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"metadata": {"type": "support"}
|
||||
})
|
||||
|
||||
# Simple message filter
|
||||
messages = honcho.get_messages(filters={
|
||||
messages = honcho.messages(filters={
|
||||
"session_id": "support-chat-1",
|
||||
"peer_id": "alice"
|
||||
})
|
||||
|
|
@ -44,19 +44,19 @@ import { Honcho } from "@honcho-ai/sdk";
|
|||
const honcho = new Honcho({});
|
||||
|
||||
// Simple peer filter
|
||||
const peers = await honcho.getPeers({
|
||||
const peers = await honcho.peers({
|
||||
filters: { peer_id: "alice" }
|
||||
});
|
||||
|
||||
// Simple session filter with metadata
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
metadata: { type: "support" }
|
||||
}
|
||||
});
|
||||
|
||||
// Simple message filter
|
||||
const messages = await honcho.getMessages({
|
||||
const messages = await honcho.messages({
|
||||
filters: {
|
||||
session_id: "support-chat-1",
|
||||
peer_id: "alice"
|
||||
|
|
@ -76,7 +76,7 @@ Use AND to require all conditions to be true:
|
|||
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
messages = honcho.get_messages(filters={
|
||||
messages = honcho.messages(filters={
|
||||
"AND": [
|
||||
{"session_id": "chat-1"},
|
||||
{"created_at": {"gte": "2024-01-01"}}
|
||||
|
|
@ -86,7 +86,7 @@ messages = honcho.get_messages(filters={
|
|||
|
||||
```typescript TypeScript
|
||||
(async () => {
|
||||
const messages = await honcho.getMessages({
|
||||
const messages = await honcho.messages({
|
||||
filters: {
|
||||
AND: [
|
||||
{ session_id: "chat-1" },
|
||||
|
|
@ -105,7 +105,7 @@ Use OR to match any of the specified conditions:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Find messages from either alice or bob
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"OR": [
|
||||
{"peer_id": "alice"},
|
||||
{"peer_id": "bob"}
|
||||
|
|
@ -113,7 +113,7 @@ messages = session.get_messages(filters={
|
|||
})
|
||||
|
||||
# Complex OR with metadata conditions
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"OR": [
|
||||
{"metadata": {"priority": "high"}},
|
||||
{"metadata": {"urgent": True}},
|
||||
|
|
@ -125,7 +125,7 @@ sessions = honcho.get_sessions(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Find messages from either alice or bob
|
||||
const messages = await session.getMessages({
|
||||
const messages = await session.messages({
|
||||
filters: {
|
||||
OR: [
|
||||
{ peer_id: "alice" },
|
||||
|
|
@ -135,7 +135,7 @@ sessions = honcho.get_sessions(filters={
|
|||
});
|
||||
|
||||
// Complex OR with metadata conditions
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
OR: [
|
||||
{ metadata: { priority: "high" } },
|
||||
|
|
@ -155,14 +155,14 @@ Use NOT to exclude specific conditions:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Find all peers except alice
|
||||
peers = honcho.get_peers(filters={
|
||||
peers = honcho.peers(filters={
|
||||
"NOT": [
|
||||
{"peer_id": "alice"}
|
||||
]
|
||||
})
|
||||
|
||||
# Find sessions that are NOT completed
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"NOT": [
|
||||
{"metadata": {"status": "completed"}}
|
||||
]
|
||||
|
|
@ -172,7 +172,7 @@ sessions = honcho.get_sessions(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Find all peers except alice
|
||||
const peers = await honcho.getPeers({
|
||||
const peers = await honcho.peers({
|
||||
filters: {
|
||||
NOT: [
|
||||
{ peer_id: "alice" }
|
||||
|
|
@ -181,7 +181,7 @@ sessions = honcho.get_sessions(filters={
|
|||
});
|
||||
|
||||
// Find sessions that are NOT completed
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
NOT: [
|
||||
{ metadata: { status: "completed" } }
|
||||
|
|
@ -199,7 +199,7 @@ Create sophisticated queries by combining different logical operators:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Find messages from alice OR bob, but NOT where message has archived set to true in metadata
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"AND": [
|
||||
{
|
||||
"OR": [
|
||||
|
|
@ -219,7 +219,7 @@ messages = session.get_messages(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Find messages from alice OR bob, but NOT where message has archived set to true in metadata
|
||||
const messages = await session.getMessages({
|
||||
const messages = await session.messages({
|
||||
filters: {
|
||||
AND: [
|
||||
{
|
||||
|
|
@ -249,12 +249,12 @@ Use comparison operators for range queries and advanced matching:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Find sessions created after a specific date
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"created_at": {"gte": "2024-01-01"}
|
||||
})
|
||||
|
||||
# Find messages within a date range
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"created_at": {
|
||||
"gte": "2024-01-01",
|
||||
"lte": "2024-12-31"
|
||||
|
|
@ -262,7 +262,7 @@ messages = session.get_messages(filters={
|
|||
})
|
||||
|
||||
# Metadata numeric comparisons
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"metadata": {
|
||||
"score": {"gt": 8.5},
|
||||
"duration": {"lte": 3600}
|
||||
|
|
@ -273,14 +273,14 @@ sessions = honcho.get_sessions(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Find sessions created after a specific date
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
created_at: { gte: "2024-01-01" }
|
||||
}
|
||||
});
|
||||
|
||||
// Find messages within a date range
|
||||
const messages = await session.getMessages({
|
||||
const messages = await session.messages({
|
||||
filters: {
|
||||
created_at: {
|
||||
gte: "2024-01-01",
|
||||
|
|
@ -290,7 +290,7 @@ sessions = honcho.get_sessions(filters={
|
|||
});
|
||||
|
||||
// Metadata numeric comparisons
|
||||
const filteredSessions = await honcho.getSessions({
|
||||
const filteredSessions = await honcho.sessions({
|
||||
filters: {
|
||||
metadata: {
|
||||
score: { gt: 8.5 },
|
||||
|
|
@ -307,19 +307,19 @@ sessions = honcho.get_sessions(filters={
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Find messages from specific peers in a session
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"peer_id": {"in": ["alice", "bob", "charlie"]}
|
||||
})
|
||||
|
||||
# Find sessions with specific tags
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"metadata": {
|
||||
"tag": {"in": ["important", "urgent", "follow-up"]}
|
||||
}
|
||||
})
|
||||
|
||||
# Not equal comparisons
|
||||
peers = honcho.get_peers(filters={
|
||||
peers = honcho.peers(filters={
|
||||
"metadata": {
|
||||
"status": {"ne": "inactive"}
|
||||
}
|
||||
|
|
@ -329,14 +329,14 @@ peers = honcho.get_peers(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Find messages from specific peers in a session
|
||||
const messages = await session.getMessages({
|
||||
const messages = await session.messages({
|
||||
filters: {
|
||||
peer_id: { in: ["alice", "bob", "charlie"] }
|
||||
}
|
||||
});
|
||||
|
||||
// Find sessions with specific tags
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
metadata: {
|
||||
tag: { in: ["important", "urgent", "follow-up"] }
|
||||
|
|
@ -345,7 +345,7 @@ peers = honcho.get_peers(filters={
|
|||
});
|
||||
|
||||
// Not equal comparisons
|
||||
const peers = await honcho.getPeers({
|
||||
const peers = await honcho.peers({
|
||||
filters: {
|
||||
metadata: {
|
||||
status: { ne: "inactive" }
|
||||
|
|
@ -365,7 +365,7 @@ Metadata filtering is particularly powerful in Honcho, supporting nested conditi
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Simple metadata equality
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"metadata": {
|
||||
"type": "customer_support",
|
||||
"priority": "high"
|
||||
|
|
@ -373,7 +373,7 @@ sessions = honcho.get_sessions(filters={
|
|||
})
|
||||
|
||||
# Nested metadata objects
|
||||
peers = honcho.get_peers(filters={
|
||||
peers = honcho.peers(filters={
|
||||
"metadata": {
|
||||
"profile": {
|
||||
"role": "admin",
|
||||
|
|
@ -386,7 +386,7 @@ peers = honcho.get_peers(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Simple metadata equality
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
metadata: {
|
||||
type: "customer_support",
|
||||
|
|
@ -396,7 +396,7 @@ peers = honcho.get_peers(filters={
|
|||
});
|
||||
|
||||
// Nested metadata objects
|
||||
const peers = await honcho.getPeers({
|
||||
const peers = await honcho.peers({
|
||||
filters: {
|
||||
metadata: {
|
||||
profile: {
|
||||
|
|
@ -419,7 +419,7 @@ If you want to do advanced queries like these, make sure not to create metadata
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Metadata with comparison operators
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"metadata": {
|
||||
"score": {"gte": 4.0, "lte": 5.0},
|
||||
"created_by": {"ne": "system"},
|
||||
|
|
@ -428,7 +428,7 @@ sessions = honcho.get_sessions(filters={
|
|||
})
|
||||
|
||||
# Complex metadata conditions
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"AND": [
|
||||
{"metadata": {"sentiment": {"in": ["positive", "neutral"]}}},
|
||||
{"metadata": {"confidence": {"gt": 0.8}}},
|
||||
|
|
@ -440,7 +440,7 @@ messages = session.get_messages(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Metadata with comparison operators
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
metadata: {
|
||||
score: { gte: 4.0, lte: 5.0 },
|
||||
|
|
@ -451,7 +451,7 @@ messages = session.get_messages(filters={
|
|||
});
|
||||
|
||||
// Complex metadata conditions
|
||||
const messages = await session.getMessages({
|
||||
const messages = await session.messages({
|
||||
filters: {
|
||||
AND: [
|
||||
{ metadata: { sentiment: { in: ["positive", "neutral"] } } },
|
||||
|
|
@ -471,17 +471,17 @@ Use wildcards (*) to match any value for a field:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Find all sessions with any peer_id (essentially all sessions)
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"peer_id": "*"
|
||||
})
|
||||
|
||||
# Wildcard in lists - matches everything
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"peer_id": {"in": ["alice", "bob", "*"]}
|
||||
})
|
||||
|
||||
# Metadata wildcards
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"metadata": {
|
||||
"type": "*", # Any type
|
||||
"status": "active" # But status must be active
|
||||
|
|
@ -492,21 +492,21 @@ sessions = honcho.get_sessions(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Find all sessions with any peer_id (essentially all sessions)
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
peer_id: "*"
|
||||
}
|
||||
});
|
||||
|
||||
// Wildcard in lists - matches everything
|
||||
const messages = await session.getMessages({
|
||||
const messages = await session.messages({
|
||||
filters: {
|
||||
peer_id: { in: ["alice", "bob", "*"] }
|
||||
}
|
||||
});
|
||||
|
||||
// Metadata wildcards
|
||||
const filteredSessions = await honcho.getSessions({
|
||||
const filteredSessions = await honcho.sessions({
|
||||
filters: {
|
||||
metadata: {
|
||||
type: "*", // Any type
|
||||
|
|
@ -525,12 +525,12 @@ sessions = honcho.get_sessions(filters={
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Find workspaces by name pattern
|
||||
workspaces = honcho.get_workspaces(filters={
|
||||
workspaces = honcho.workspaces(filters={
|
||||
"name": {"contains": "prod"}
|
||||
})
|
||||
|
||||
# Filter by metadata
|
||||
workspaces = honcho.get_workspaces(filters={
|
||||
workspaces = honcho.workspaces(filters={
|
||||
"metadata": {
|
||||
"environment": "production",
|
||||
"team": {"in": ["backend", "frontend", "devops"]}
|
||||
|
|
@ -541,14 +541,14 @@ workspaces = honcho.get_workspaces(filters={
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Find workspaces by name pattern
|
||||
const workspaces = await honcho.getWorkspaces({
|
||||
const workspaces = await honcho.workspaces({
|
||||
filters: {
|
||||
name: { contains: "prod" }
|
||||
}
|
||||
});
|
||||
|
||||
// Filter by metadata
|
||||
const workspaces = await honcho.getWorkspaces({
|
||||
const workspaces = await honcho.workspaces({
|
||||
filters: {
|
||||
metadata: {
|
||||
environment: "production",
|
||||
|
|
@ -568,7 +568,7 @@ workspaces = honcho.get_workspaces(filters={
|
|||
from datetime import datetime, timedelta
|
||||
|
||||
week_ago = (datetime.now() - timedelta(days=7)).isoformat()
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"AND": [
|
||||
{"content": {"icontains": "error"}},
|
||||
{"created_at": {"gte": week_ago}},
|
||||
|
|
@ -577,7 +577,7 @@ messages = session.get_messages(filters={
|
|||
})
|
||||
|
||||
# Find messages in specific sessions with sentiment analysis
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"AND": [
|
||||
{"session_id": {"in": ["support-1", "support-2", "support-3"]}},
|
||||
{"metadata": {"sentiment": "negative"}},
|
||||
|
|
@ -590,7 +590,7 @@ messages = session.get_messages(filters={
|
|||
(async () => {
|
||||
// Find error messages from the last week
|
||||
const weekAgo = new Date(Date.now() - 7 * 24 * 60 * 60 * 1000).toISOString();
|
||||
const messages = await session.getMessages({
|
||||
const messages = await session.messages({
|
||||
filters: {
|
||||
AND: [
|
||||
{ content: { icontains: "error" } },
|
||||
|
|
@ -601,7 +601,7 @@ messages = session.get_messages(filters={
|
|||
});
|
||||
|
||||
// Find messages in specific sessions with sentiment analysis
|
||||
const sentimentMessages = await session.getMessages({
|
||||
const sentimentMessages = await session.messages({
|
||||
filters: {
|
||||
AND: [
|
||||
{ session_id: { in: ["support-1", "support-2", "support-3"] } },
|
||||
|
|
@ -624,7 +624,7 @@ from honcho.exceptions import FilterError
|
|||
|
||||
try:
|
||||
# Invalid filter - unsupported operator
|
||||
messages = session.get_messages(filters={
|
||||
messages = session.messages(filters={
|
||||
"created_at": {"invalid_operator": "2024-01-01"}
|
||||
})
|
||||
except FilterError as e:
|
||||
|
|
@ -633,7 +633,7 @@ except FilterError as e:
|
|||
|
||||
try:
|
||||
# Invalid column name
|
||||
sessions = honcho.get_sessions(filters={
|
||||
sessions = honcho.sessions(filters={
|
||||
"nonexistent_field": "value"
|
||||
})
|
||||
except FilterError as e:
|
||||
|
|
@ -644,7 +644,7 @@ except FilterError as e:
|
|||
(async () => {
|
||||
try {
|
||||
// Invalid filter - unsupported operator
|
||||
const messages = await session.getMessages({
|
||||
const messages = await session.messages({
|
||||
filters: {
|
||||
created_at: { invalid_operator: "2024-01-01" }
|
||||
}
|
||||
|
|
@ -658,7 +658,7 @@ except FilterError as e:
|
|||
|
||||
try {
|
||||
// Invalid column name
|
||||
const sessions = await honcho.getSessions({
|
||||
const sessions = await honcho.sessions({
|
||||
filters: {
|
||||
nonexistent_field: "value"
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,10 +1,10 @@
|
|||
---
|
||||
title: 'Get Context'
|
||||
description: 'Learn how to use get_context() to retrieve and format conversation context for LLM integration'
|
||||
description: 'Learn how to use context() to retrieve and format conversation context for LLM integration'
|
||||
icon: 'messages'
|
||||
---
|
||||
|
||||
The `get_context()` method is a powerful feature that retrieves formatted conversation context from sessions, making it easy to integrate with LLMs like OpenAI, Anthropic, and others. This guide covers everything you need to know about working with session context.
|
||||
The `context()` method is a powerful feature that retrieves formatted conversation context from sessions, making it easy to integrate with LLMs like OpenAI, Anthropic, and others. This guide covers everything you need to know about working with session context.
|
||||
|
||||
<Note>
|
||||
By default, the context includes a blend of summary and messages ***which covers the entire session history of a peer***.
|
||||
|
|
@ -14,7 +14,7 @@ Summaries are automatically generated at intervals and recent messages are inclu
|
|||
|
||||
## Basic Usage
|
||||
|
||||
The `get_context()` method is available on all Session objects and returns a `SessionContext` that contains the formatted conversation history.
|
||||
The `context()` method is available on all Session objects and returns a `SessionContext` that contains the formatted conversation history.
|
||||
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
|
|
@ -25,7 +25,7 @@ honcho = Honcho()
|
|||
session = honcho.session("conversation-1")
|
||||
|
||||
# Get basic context (not very useful before adding any messages!)
|
||||
context = session.get_context()
|
||||
context = session.context()
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
|
|
@ -37,14 +37,14 @@ import { Honcho } from "@honcho-ai/sdk";
|
|||
const session = await honcho.session("conversation-1");
|
||||
|
||||
// Get basic context (not very useful before adding any messages!)
|
||||
const context = await session.getContext();
|
||||
const context = await session.context();
|
||||
})();
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
## Context Parameters
|
||||
|
||||
The `get_context()` method accepts several optional parameters to customize the retrieved context:
|
||||
The `context()` method accepts several optional parameters to customize the retrieved context:
|
||||
|
||||
### Token Limits
|
||||
|
||||
|
|
@ -53,19 +53,19 @@ Control the size of the context by setting a maximum token count:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Limit context to 1500 tokens
|
||||
context = session.get_context(tokens=1500)
|
||||
context = session.context(tokens=1500)
|
||||
|
||||
# Limit context to 3000 tokens for larger conversations
|
||||
context = session.get_context(tokens=3000)
|
||||
context = session.context(tokens=3000)
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Limit context to 1500 tokens
|
||||
const context = await session.getContext({ tokens: 1500 });
|
||||
const context = await session.context({ tokens: 1500 });
|
||||
|
||||
// Limit context to 3000 tokens for larger conversations
|
||||
const context = await session.getContext({ tokens: 3000 });
|
||||
const context = await session.context({ tokens: 3000 });
|
||||
})();
|
||||
```
|
||||
</CodeGroup>
|
||||
|
|
@ -77,19 +77,19 @@ Enable summary mode (on by default) to get a condensed version of the conversati
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Get context with summary enabled -- will contain both summary and messages
|
||||
context = session.get_context(summary=True)
|
||||
context = session.context(summary=True)
|
||||
|
||||
# Combine summary=False with token limits to get more messages
|
||||
context = session.get_context(summary=False, tokens=2000)
|
||||
context = session.context(summary=False, tokens=2000)
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Get context with summary enabled -- will contain both summary and messages
|
||||
const context = await session.getContext({ summary: true });
|
||||
const context = await session.context({ summary: true });
|
||||
|
||||
// Combine summary=False with token limits to get more messages
|
||||
const context = await session.getContext({
|
||||
const context = await session.context({
|
||||
summary: false,
|
||||
tokens: 2000
|
||||
});
|
||||
|
|
@ -104,7 +104,7 @@ You can include a peer's [representation](/v3/documentation/core-concepts/repres
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Get context with peer representation included
|
||||
context = session.get_context(
|
||||
context = session.context(
|
||||
tokens=2000,
|
||||
peer_target="user-123" # Include representation of user-123
|
||||
)
|
||||
|
|
@ -114,7 +114,7 @@ print(context.peer_representation) # String representation
|
|||
print(context.peer_card) # List of peer card items
|
||||
|
||||
# Get representation from a specific peer's perspective
|
||||
context = session.get_context(
|
||||
context = session.context(
|
||||
tokens=2000,
|
||||
peer_target="user-123",
|
||||
peer_perspective="assistant" # From assistant's viewpoint
|
||||
|
|
@ -124,7 +124,7 @@ context = session.get_context(
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Get context with peer representation included
|
||||
const context = await session.getContext({
|
||||
const context = await session.context({
|
||||
tokens: 2000,
|
||||
peerTarget: "user-123" // Include representation of user-123
|
||||
});
|
||||
|
|
@ -134,7 +134,7 @@ context = session.get_context(
|
|||
console.log(context.peerCard); // Array of peer card items
|
||||
|
||||
// Get representation from a specific peer's perspective
|
||||
const perspectiveContext = await session.getContext({
|
||||
const perspectiveContext = await session.context({
|
||||
tokens: 2000,
|
||||
peerTarget: "user-123",
|
||||
peerPerspective: "assistant" // From assistant's viewpoint
|
||||
|
|
@ -149,7 +149,7 @@ Use `search_query` to fetch semantically relevant conclusions based on a query s
|
|||
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
context = session.get_context(
|
||||
context = session.context(
|
||||
tokens=2000,
|
||||
peer_target="user-123",
|
||||
search_query="What are my coding preferences?",
|
||||
|
|
@ -162,7 +162,7 @@ context = session.get_context(
|
|||
|
||||
```typescript TypeScript
|
||||
(async () => {
|
||||
const context = await session.getContext({
|
||||
const context = await session.context({
|
||||
tokens: 2000,
|
||||
peerTarget: "user-123",
|
||||
searchQuery: "What are my coding preferences?",
|
||||
|
|
@ -184,7 +184,7 @@ Use `limit_to_session` to only include conclusions from the current session:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Get context limited to this session's conclusions only
|
||||
context = session.get_context(
|
||||
context = session.context(
|
||||
tokens=2000,
|
||||
peer_target="user-123",
|
||||
limit_to_session=True # Only conclusions from this session
|
||||
|
|
@ -194,7 +194,7 @@ context = session.get_context(
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Get context limited to this session's conclusions only
|
||||
const context = await session.getContext({
|
||||
const context = await session.context({
|
||||
tokens: 2000,
|
||||
peerTarget: "user-123",
|
||||
limitToSession: true // Only conclusions from this session
|
||||
|
|
@ -239,7 +239,7 @@ session.add_messages([
|
|||
])
|
||||
|
||||
# Get context and convert to OpenAI format
|
||||
context = session.get_context()
|
||||
context = session.context()
|
||||
openai_messages = context.to_openai(assistant=assistant)
|
||||
|
||||
# The messages are now ready for OpenAI API
|
||||
|
|
@ -263,7 +263,7 @@ print(openai_messages)
|
|||
]);
|
||||
|
||||
// Get context and convert to OpenAI format
|
||||
const context = await session.getContext();
|
||||
const context = await session.context();
|
||||
const openaiMessages = context.toOpenAI(assistant);
|
||||
|
||||
// The messages are now ready for OpenAI API
|
||||
|
|
@ -283,7 +283,7 @@ Convert context to Anthropic's Claude format:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Get context and convert to Anthropic format
|
||||
context = session.get_context()
|
||||
context = session.context()
|
||||
anthropic_messages = context.to_anthropic(assistant=assistant)
|
||||
|
||||
# Ready for Anthropic API
|
||||
|
|
@ -293,7 +293,7 @@ print(anthropic_messages)
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Get context and convert to Anthropic format
|
||||
const context = await session.getContext();
|
||||
const context = await session.context();
|
||||
const anthropicMessages = context.toAnthropic(assistant);
|
||||
|
||||
// Ready for Anthropic API
|
||||
|
|
@ -328,7 +328,7 @@ session.add_messages([
|
|||
])
|
||||
|
||||
# Get context for LLM
|
||||
messages = session.get_context(tokens=2000).to_openai(assistant=assistant)
|
||||
messages = session.context(tokens=2000).to_openai(assistant=assistant)
|
||||
|
||||
# Add new user message and get AI response
|
||||
messages.append({
|
||||
|
|
@ -370,7 +370,7 @@ import { Honcho } from "@honcho-ai/sdk";
|
|||
]);
|
||||
|
||||
// Get context for LLM
|
||||
const messages = (await session.getContext({ tokens: 2000 })).toOpenAI(assistant);
|
||||
const messages = (await session.context({ tokens: 2000 })).toOpenAI(assistant);
|
||||
|
||||
// Add new user message and get AI response
|
||||
const response = await openai.chat.completions.create({
|
||||
|
|
@ -395,7 +395,7 @@ import { Honcho } from "@honcho-ai/sdk";
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
def chat_loop():
|
||||
"""Example of a continuous chat loop using get_context()"""
|
||||
"""Example of a continuous chat loop using context()"""
|
||||
|
||||
session = honcho.session("chat-session")
|
||||
user = honcho.peer("user")
|
||||
|
|
@ -411,7 +411,7 @@ def chat_loop():
|
|||
session.add_messages([user.message(user_input)])
|
||||
|
||||
# Get conversation context
|
||||
context = session.get_context(tokens=2000)
|
||||
context = session.context(tokens=2000)
|
||||
messages = context.to_openai(assistant=assistant)
|
||||
|
||||
# Get AI response
|
||||
|
|
@ -451,7 +451,7 @@ chat_loop()
|
|||
await session.addMessages([user.message(userInput)]);
|
||||
|
||||
// Get conversation context
|
||||
const context = await session.getContext({ tokens: 2000 });
|
||||
const context = await session.context({ tokens: 2000 });
|
||||
const messages = context.toOpenAI(assistant);
|
||||
|
||||
// Get AI response
|
||||
|
|
@ -486,7 +486,7 @@ For very long conversations, use summaries to maintain context while controlling
|
|||
long_session = honcho.session("long-conversation")
|
||||
|
||||
# Get summarized context to fit within token limits
|
||||
context = long_session.get_context(summary=True, tokens=1500)
|
||||
context = long_session.context(summary=True, tokens=1500)
|
||||
messages = context.to_openai(assistant=assistant)
|
||||
|
||||
# This will include a summary of older messages and recent full messages
|
||||
|
|
@ -499,7 +499,7 @@ print(f"Context contains {len(messages)} formatted messages")
|
|||
const longSession = await honcho.session("long-conversation");
|
||||
|
||||
// Get summarized context to fit within token limits
|
||||
const context = await longSession.getContext({
|
||||
const context = await longSession.context({
|
||||
summary: true,
|
||||
tokens: 1500
|
||||
});
|
||||
|
|
@ -523,9 +523,9 @@ analyzer = honcho.peer("data-analyzer")
|
|||
moderator = honcho.peer("moderator")
|
||||
|
||||
# Get context formatted for each assistant type
|
||||
chatbot_context = session.get_context().to_openai(assistant=chatbot)
|
||||
analyzer_context = session.get_context().to_openai(assistant=analyzer)
|
||||
moderator_context = session.get_context().to_openai(assistant=moderator)
|
||||
chatbot_context = session.context().to_openai(assistant=chatbot)
|
||||
analyzer_context = session.context().to_openai(assistant=analyzer)
|
||||
moderator_context = session.context().to_openai(assistant=moderator)
|
||||
|
||||
# Each context will format the conversation from that assistant's perspective
|
||||
```
|
||||
|
|
@ -538,7 +538,7 @@ moderator_context = session.get_context().to_openai(assistant=moderator)
|
|||
const moderator = await honcho.peer("moderator");
|
||||
|
||||
// Get context formatted for each assistant type
|
||||
const context = await session.getContext();
|
||||
const context = await session.context();
|
||||
const chatbotContext = context.toOpenAI(chatbot);
|
||||
const analyzerContext = context.toOpenAI(analyzer);
|
||||
const moderatorContext = context.toOpenAI(moderator);
|
||||
|
|
@ -557,21 +557,21 @@ Always set appropriate token limits to control costs and ensure context fits wit
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Good: Set reasonable token limits based on your model
|
||||
context = session.get_context(tokens=3000) # For GPT-4
|
||||
context = session.get_context(tokens=1500) # For smaller models
|
||||
context = session.context(tokens=3000) # For GPT-4
|
||||
context = session.context(tokens=1500) # For smaller models
|
||||
|
||||
# Good: Use summaries for very long conversations
|
||||
context = session.get_context(summary=True, tokens=2000)
|
||||
context = session.context(summary=True, tokens=2000)
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Good: Set reasonable token limits based on your model
|
||||
const context = await session.getContext({ tokens: 3000 }); // For GPT-4
|
||||
const context = await session.getContext({ tokens: 1500 }); // For smaller models
|
||||
const context = await session.context({ tokens: 3000 }); // For GPT-4
|
||||
const context = await session.context({ tokens: 1500 }); // For smaller models
|
||||
|
||||
// Good: Use summaries for very long conversations
|
||||
const context = await session.getContext({ summary: true, tokens: 2000 });
|
||||
const context = await session.context({ summary: true, tokens: 2000 });
|
||||
})();
|
||||
```
|
||||
</CodeGroup>
|
||||
|
|
@ -583,7 +583,7 @@ For applications with frequent context retrieval, consider caching context when
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Cache context for multiple LLM calls within the same request
|
||||
context = session.get_context(tokens=2000)
|
||||
context = session.context(tokens=2000)
|
||||
openai_messages = context.to_openai(assistant=assistant)
|
||||
anthropic_messages = context.to_anthropic(assistant=assistant)
|
||||
|
||||
|
|
@ -593,7 +593,7 @@ anthropic_messages = context.to_anthropic(assistant=assistant)
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
// Cache context for multiple LLM calls within the same request
|
||||
const context = await session.getContext({ tokens: 2000 });
|
||||
const context = await session.context({ tokens: 2000 });
|
||||
const openaiMessages = context.toOpenAI(assistant);
|
||||
const anthropicMessages = context.toAnthropic(assistant);
|
||||
|
||||
|
|
@ -609,7 +609,7 @@ Always handle potential errors when retrieving context:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
try:
|
||||
context = session.get_context(tokens=2000)
|
||||
context = session.context(tokens=2000)
|
||||
except Exception as e:
|
||||
print(f"Error getting context: {e}")
|
||||
# Handle error appropriately (fallback to basic context, retry, etc.)
|
||||
|
|
@ -618,7 +618,7 @@ except Exception as e:
|
|||
```typescript TypeScript
|
||||
(async () => {
|
||||
try {
|
||||
const context = await session.getContext({ tokens: 2000 });
|
||||
const context = await session.context({ tokens: 2000 });
|
||||
} catch (error) {
|
||||
console.error(`Error getting context: ${error}`);
|
||||
// Handle error appropriately (fallback to basic context, retry, etc.)
|
||||
|
|
@ -629,7 +629,7 @@ except Exception as e:
|
|||
|
||||
## Conclusion
|
||||
|
||||
The `get_context()` method is essential for integrating Honcho sessions with LLMs. By understanding how to:
|
||||
The `context()` method is essential for integrating Honcho sessions with LLMs. By understanding how to:
|
||||
|
||||
- Retrieve context with appropriate parameters
|
||||
- Convert context to LLM-specific formats
|
||||
|
|
|
|||
|
|
@ -62,7 +62,7 @@ session.add_messages([
|
|||
response = alice.chat("What did the assistant tell this user about the weather?")
|
||||
|
||||
# Get conversation context for LLM completions
|
||||
context = session.get_context()
|
||||
context = session.context()
|
||||
openai_messages = context.to_openai(assistant=assistant)
|
||||
```
|
||||
|
||||
|
|
@ -89,7 +89,7 @@ await session.addMessages([
|
|||
const response = await alice.chat("What did the assistant tell this user about the weather?");
|
||||
|
||||
// Get conversation context for LLM completions
|
||||
const context = await session.getContext();
|
||||
const context = await session.context();
|
||||
const openaiMessages = context.toOpenAI(assistant);
|
||||
```
|
||||
</CodeGroup>
|
||||
|
|
@ -192,10 +192,10 @@ peer = honcho.peer(id)
|
|||
session = honcho.session(id)
|
||||
|
||||
# List all peers in workspace
|
||||
peers = honcho.get_peers()
|
||||
peers = honcho.peers()
|
||||
|
||||
# List all sessions in workspace
|
||||
sessions = honcho.get_sessions()
|
||||
sessions = honcho.sessions()
|
||||
|
||||
# Search across all content in workspace
|
||||
results = honcho.search(query)
|
||||
|
|
@ -205,7 +205,7 @@ metadata = honcho.get_metadata()
|
|||
honcho.set_metadata(dict)
|
||||
|
||||
# Get list of all workspace IDs
|
||||
workspaces = honcho.get_workspaces()
|
||||
workspaces = honcho.workspaces()
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
|
|
@ -216,10 +216,10 @@ const peer = await honcho.peer(id);
|
|||
const session = await honcho.session(id);
|
||||
|
||||
// List all peers in workspace (returns Page<Peer>)
|
||||
const peers = await honcho.getPeers();
|
||||
const peers = await honcho.peers();
|
||||
|
||||
// List all sessions in workspace (returns Page<Session>)
|
||||
const sessions = await honcho.getSessions();
|
||||
const sessions = await honcho.sessions();
|
||||
|
||||
// Search across all content in workspace (returns Page<any>)
|
||||
const results = await honcho.search(query);
|
||||
|
|
@ -229,7 +229,7 @@ const metadata = await honcho.getMetadata();
|
|||
await honcho.setMetadata(metadata);
|
||||
|
||||
// Get list of all workspace IDs
|
||||
const workspaces = await honcho.getWorkspaces();
|
||||
const workspaces = await honcho.workspaces();
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
|
|
@ -269,7 +269,7 @@ session.add_messages([
|
|||
])
|
||||
|
||||
# Get peer's sessions
|
||||
sessions = alice.get_sessions()
|
||||
sessions = alice.sessions()
|
||||
|
||||
# Search peer's messages
|
||||
results = alice.search("programming")
|
||||
|
|
@ -280,11 +280,11 @@ metadata["location"] = "Paris"
|
|||
alice.set_metadata(metadata)
|
||||
|
||||
# Get peer context (representation + peer card in one call)
|
||||
context = alice.get_context()
|
||||
context = alice.get_context(target="bob") # What alice knows about bob
|
||||
context = alice.context()
|
||||
context = alice.context(target="bob") # What alice knows about bob
|
||||
|
||||
# Get working representation with semantic search
|
||||
rep = alice.get_representation(search_query="preferences", search_top_k=10)
|
||||
rep = alice.representation(search_query="preferences", search_top_k=10)
|
||||
|
||||
# Access conclusions
|
||||
self_conclusions = alice.conclusions.list() # Self-conclusions
|
||||
|
|
@ -318,7 +318,7 @@ await session.addMessages([
|
|||
]);
|
||||
|
||||
// Get peer's sessions
|
||||
const sessions = await alice.getSessions();
|
||||
const sessions = await alice.sessions();
|
||||
|
||||
// Search peer's messages
|
||||
const results = await alice.search("programming");
|
||||
|
|
@ -331,11 +331,11 @@ await alice.setMetadata({
|
|||
});
|
||||
|
||||
// Get peer context (representation + peer card in one call)
|
||||
const context = await alice.getContext();
|
||||
const targetContext = await alice.getContext("bob"); // What alice knows about bob
|
||||
const context = await alice.context();
|
||||
const targetContext = await alice.context({ target: "bob" }); // What alice knows about bob
|
||||
|
||||
// Get working representation with semantic search
|
||||
const rep = await alice.getRepresentation(undefined, undefined, {
|
||||
const rep = await alice.representation({
|
||||
searchQuery: "preferences",
|
||||
searchTopK: 10
|
||||
});
|
||||
|
|
@ -348,20 +348,20 @@ const bobConclusions = await alice.conclusionsOf("bob").list(); // Conclusions
|
|||
|
||||
### Peer Context
|
||||
|
||||
The `get_context()` method on peers retrieves both the working representation and peer card in a single API call:
|
||||
The `context()` method on peers retrieves both the working representation and peer card in a single API call:
|
||||
|
||||
<CodeGroup>
|
||||
```python Python
|
||||
# Get peer's own context
|
||||
context = alice.get_context()
|
||||
context = alice.context()
|
||||
print(context.representation) # Working representation
|
||||
print(context.peer_card) # Peer card as list of strings
|
||||
|
||||
# Get context about another peer (what alice knows about bob)
|
||||
bob_context = alice.get_context(target="bob")
|
||||
bob_context = alice.context(target="bob")
|
||||
|
||||
# Get context with semantic search
|
||||
context = alice.get_context(
|
||||
context = alice.context(
|
||||
target="bob",
|
||||
search_query="work preferences",
|
||||
search_top_k=10,
|
||||
|
|
@ -373,15 +373,16 @@ context = alice.get_context(
|
|||
|
||||
```typescript TypeScript
|
||||
// Get peer's own context
|
||||
const context = await alice.getContext();
|
||||
const context = await alice.context();
|
||||
console.log(context.representation); // Working representation
|
||||
console.log(context.peerCard); // Peer card as array of strings
|
||||
|
||||
// Get context about another peer (what alice knows about bob)
|
||||
const bobContext = await alice.getContext("bob");
|
||||
const bobContext = await alice.context({ target: "bob" });
|
||||
|
||||
// Get context with semantic search
|
||||
const searchedContext = await alice.getContext("bob", {
|
||||
const searchedContext = await alice.context({
|
||||
target: "bob",
|
||||
searchQuery: "work preferences",
|
||||
searchTopK: 10,
|
||||
searchMaxDistance: 0.8,
|
||||
|
|
@ -512,9 +513,9 @@ session.set_peers([alice, bob, charlie]) # Replace all peers
|
|||
session.remove_peers([alice])
|
||||
|
||||
# Get session peers and their configurations
|
||||
peers = session.get_peers()
|
||||
peer_config = session.get_peer_config(alice)
|
||||
session.set_peer_config(alice, SessionPeerConfig(observe_me=False))
|
||||
peers = session.peers()
|
||||
peer_config = session.get_peer_configuration(alice)
|
||||
session.set_peer_configuration(alice, SessionPeerConfig(observe_me=False))
|
||||
|
||||
# Message management
|
||||
session.add_messages([
|
||||
|
|
@ -523,13 +524,13 @@ session.add_messages([
|
|||
])
|
||||
|
||||
# Get messages
|
||||
messages = session.get_messages()
|
||||
messages = session.messages()
|
||||
|
||||
# Get conversation context
|
||||
context = session.get_context(summary=True, tokens=2000)
|
||||
context = session.context(summary=True, tokens=2000)
|
||||
|
||||
# Get context with peer representation included
|
||||
context = session.get_context(
|
||||
context = session.context(
|
||||
tokens=2000,
|
||||
peer_target="user",
|
||||
peer_perspective="assistant",
|
||||
|
|
@ -545,9 +546,9 @@ context = session.get_context(
|
|||
results = session.search("help")
|
||||
|
||||
# Working representation queries with semantic search
|
||||
global_rep = session.get_representation("alice")
|
||||
targeted_rep = session.get_representation(alice, target=bob)
|
||||
searched_rep = session.get_representation(
|
||||
global_rep = session.representation("alice")
|
||||
targeted_rep = session.representation(alice, target=bob)
|
||||
searched_rep = session.representation(
|
||||
"alice",
|
||||
search_query="preferences",
|
||||
search_top_k=10,
|
||||
|
|
@ -593,7 +594,7 @@ await session.removePeers([alice]);
|
|||
await session.removePeers("single-peer-id");
|
||||
|
||||
// Get session peers
|
||||
const peers = await session.getPeers();
|
||||
const peers = await session.peers();
|
||||
|
||||
// Message management
|
||||
await session.addMessages([
|
||||
|
|
@ -602,13 +603,13 @@ await session.addMessages([
|
|||
]);
|
||||
|
||||
// Get messages
|
||||
const messages = await session.getMessages();
|
||||
const messages = await session.messages();
|
||||
|
||||
// Get conversation context
|
||||
const context = await session.getContext({ summary: true, tokens: 2000 });
|
||||
const context = await session.context({ summary: true, tokens: 2000 });
|
||||
|
||||
// Get context with peer representation included
|
||||
const richContext = await session.getContext({
|
||||
const richContext = await session.context({
|
||||
tokens: 2000,
|
||||
peerTarget: "user",
|
||||
peerPerspective: "assistant",
|
||||
|
|
@ -616,7 +617,7 @@ const richContext = await session.getContext({
|
|||
limitToSession: true,
|
||||
searchTopK: 10,
|
||||
searchMaxDistance: 0.8,
|
||||
includeMostDerived: true,
|
||||
includeMostFrequent: true,
|
||||
maxConclusions: 25
|
||||
});
|
||||
|
||||
|
|
@ -624,12 +625,12 @@ const richContext = await session.getContext({
|
|||
const results = await session.search("help");
|
||||
|
||||
// Working representation queries with semantic search
|
||||
const globalRep = await session.getRepresentation("alice");
|
||||
const targetedRep = await session.getRepresentation(alice, { target: bob });
|
||||
const searchedRep = await session.getRepresentation("alice", undefined, {
|
||||
const globalRep = await session.representation("alice");
|
||||
const targetedRep = await session.representation(alice, { target: bob });
|
||||
const searchedRep = await session.representation("alice", {
|
||||
searchQuery: "preferences",
|
||||
searchTopK: 10,
|
||||
includeMostDerived: true
|
||||
includeMostFrequent: true
|
||||
});
|
||||
|
||||
// Upload a file to create messages
|
||||
|
|
@ -699,7 +700,7 @@ Provides formatted conversation context for LLM integration:
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Get session context
|
||||
context = session.get_context(summary=True, tokens=1500)
|
||||
context = session.context(summary=True, tokens=1500)
|
||||
|
||||
# Convert to LLM-friendly formats
|
||||
openai_messages = context.to_openai(assistant=assistant)
|
||||
|
|
@ -708,7 +709,7 @@ anthropic_messages = context.to_anthropic(assistant=assistant)
|
|||
|
||||
```typescript TypeScript
|
||||
// Get session context
|
||||
const context = await session.getContext({ summary: true, tokens: 1500 });
|
||||
const context = await session.context({ summary: true, tokens: 1500 });
|
||||
|
||||
// Convert to LLM-friendly formats
|
||||
const openaiMessages = context.toOpenAI(assistant);
|
||||
|
|
@ -818,7 +819,7 @@ const moderatorView = await moderator.chat("What feedback am I getting?", {
|
|||
import openai
|
||||
|
||||
# Get conversation context
|
||||
context = session.get_context(tokens=3000)
|
||||
context = session.context(tokens=3000)
|
||||
messages = context.to_openai(assistant=assistant)
|
||||
|
||||
# Call OpenAI API
|
||||
|
|
@ -836,7 +837,7 @@ import OpenAI from 'openai';
|
|||
const openai = new OpenAI();
|
||||
|
||||
// Get conversation context
|
||||
const context = await session.getContext({ tokens: 3000 });
|
||||
const context = await session.context({ tokens: 3000 });
|
||||
const messages = context.toOpenAI(assistant);
|
||||
|
||||
// Call OpenAI API
|
||||
|
|
@ -896,8 +897,8 @@ session.add_messages([
|
|||
])
|
||||
|
||||
# Filter messages by metadata
|
||||
finance_messages = session.get_messages(filters={"metadata": {"topic": "finance"}})
|
||||
action_items = session.get_messages(filters={"metadata": {"action_item": True}})
|
||||
finance_messages = session.messages(filters={"metadata": {"topic": "finance"}})
|
||||
action_items = session.messages(filters={"metadata": {"action_item": True}})
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
|
|
@ -918,10 +919,10 @@ await session.addMessages([
|
|||
]);
|
||||
|
||||
// Filter messages by metadata
|
||||
const financeMessages = await session.getMessages({
|
||||
const financeMessages = await session.messages({
|
||||
filters: { metadata: { topic: "finance" } }
|
||||
});
|
||||
const actionItems = await session.getMessages({
|
||||
const actionItems = await session.messages({
|
||||
filters: { metadata: { action_item: true } }
|
||||
});
|
||||
```
|
||||
|
|
@ -932,17 +933,17 @@ const actionItems = await session.getMessages({
|
|||
<CodeGroup>
|
||||
```python Python
|
||||
# Iterate through all sessions
|
||||
for session in honcho.get_sessions():
|
||||
for session in honcho.sessions():
|
||||
print(f"Session: {session.id}")
|
||||
|
||||
# Iterate through session messages
|
||||
for message in session.get_messages():
|
||||
for message in session.messages():
|
||||
print(f" {message.peer_id}: {message.content}")
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
// Get paginated results
|
||||
const peersPage = await honcho.getPeers();
|
||||
const peersPage = await honcho.peers();
|
||||
|
||||
// Iterate through all items
|
||||
for await (const peer of peersPage) {
|
||||
|
|
@ -996,7 +997,7 @@ peers = [honcho.peer(f"user-{i}") for i in range(100)] # Fast
|
|||
session.add_messages([peer.message(f"Message {i}") for i, peer in enumerate(peers)])
|
||||
|
||||
# Use context limits to control token usage
|
||||
context = session.get_context(tokens=1500) # Limit context size
|
||||
context = session.context(tokens=1500) # Limit context size
|
||||
```
|
||||
|
||||
```typescript TypeScript
|
||||
|
|
@ -1011,10 +1012,10 @@ await session.addMessages(
|
|||
);
|
||||
|
||||
// Use context limits to control token usage
|
||||
const context = await session.getContext({ tokens: 1500 }); // Limit context size
|
||||
const context = await session.context({ tokens: 1500 }); // Limit context size
|
||||
|
||||
// Iterate efficiently with async iteration
|
||||
for await (const peer of await honcho.getPeers()) {
|
||||
for await (const peer of await honcho.peers()) {
|
||||
// Process one peer at a time without loading all into memory
|
||||
}
|
||||
```
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ Unlike basic message retrieval, memory-enhanced context:
|
|||
Automatically manages context to fit within your specified token budget:
|
||||
|
||||
```python
|
||||
context = session.get_context(tokens=2000)
|
||||
context = session.context(tokens=2000)
|
||||
```
|
||||
|
||||
### Multi-Layered Context
|
||||
|
|
@ -42,7 +42,7 @@ Combines multiple information sources:
|
|||
Fine-tune what context is included:
|
||||
|
||||
```python
|
||||
context = session.get_context(
|
||||
context = session.context(
|
||||
tokens=2000,
|
||||
include_summaries=True,
|
||||
include_representation=True,
|
||||
|
|
@ -58,7 +58,7 @@ Provide your agent with rich context for personalized responses:
|
|||
|
||||
```python
|
||||
# Get optimized context
|
||||
context = session.get_context(tokens=1500)
|
||||
context = session.context(tokens=1500)
|
||||
|
||||
# Use in your LLM prompt
|
||||
response = llm.generate(
|
||||
|
|
@ -75,10 +75,10 @@ Get context tailored to specific participants:
|
|||
|
||||
```python
|
||||
# Get Alice's perspective
|
||||
alice_context = session.get_context(peer_id=alice.id)
|
||||
alice_context = session.context(peer_id=alice.id)
|
||||
|
||||
# Get Bob's perspective
|
||||
bob_context = session.get_context(peer_id=bob.id)
|
||||
bob_context = session.context(peer_id=bob.id)
|
||||
```
|
||||
|
||||
### Dynamic Context Windows
|
||||
|
|
@ -87,10 +87,10 @@ Adjust context size based on task complexity:
|
|||
|
||||
```python
|
||||
# More context for complex tasks
|
||||
detailed_context = session.get_context(tokens=4000)
|
||||
detailed_context = session.context(tokens=4000)
|
||||
|
||||
# Minimal context for simple queries
|
||||
quick_context = session.get_context(tokens=500)
|
||||
quick_context = session.context(tokens=500)
|
||||
```
|
||||
|
||||
## How It Works
|
||||
|
|
@ -111,7 +111,7 @@ Leave room in your model's context window:
|
|||
|
||||
```python
|
||||
# For a 8K context model
|
||||
context = session.get_context(tokens=2000) # Leaves room for prompt + response
|
||||
context = session.context(tokens=2000) # Leaves room for prompt + response
|
||||
```
|
||||
|
||||
### Representation Updates
|
||||
|
|
@ -132,7 +132,7 @@ Context can be cached for repeated queries:
|
|||
|
||||
```python
|
||||
# Cache context for multiple agent calls
|
||||
cached_context = session.get_context(tokens=2000)
|
||||
cached_context = session.context(tokens=2000)
|
||||
|
||||
# Reuse for multiple related queries
|
||||
for query in user_queries:
|
||||
|
|
|
|||
|
|
@ -124,7 +124,7 @@ def llm(session, prompt) -> str:
|
|||
|
||||
You should expand this function with custom logic, prompts, etc.
|
||||
"""
|
||||
messages: list[dict[str, object]] = session.get_context().to_openai(
|
||||
messages: list[dict[str, object]] = session.context().to_openai(
|
||||
assistant=assistant
|
||||
)
|
||||
messages.append({"role": "user", "content": prompt})
|
||||
|
|
@ -246,7 +246,7 @@ openai = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=MODEL_API_KEY)
|
|||
The new Honcho peer/session API makes Discord bot integration much simpler and more intuitive. Key patterns we learned:
|
||||
|
||||
- **Peer/Session Model**: Users are represented as peers, conversations as sessions
|
||||
- **Automatic Context Management**: `session.get_context().to_openai()` automatically formats chat history
|
||||
- **Automatic Context Management**: `session.context().to_openai()` automatically formats chat history
|
||||
- **Message Storage**: `session.add_messages()` stores both user and assistant messages
|
||||
- **Representation Queries**: `peer.chat()` enables querying conversation history
|
||||
- **Helper Functions**: Clean code organization with focused helper functions
|
||||
|
|
|
|||
|
|
@ -128,7 +128,7 @@ response = user.chat("What does the quarterly report say about revenue growth?")
|
|||
print(response)
|
||||
|
||||
# Get context from the uploaded documents for LLM integration
|
||||
context = session.get_context(tokens=3000)
|
||||
context = session.context(tokens=3000)
|
||||
messages = context.to_openai(assistant=assistant)
|
||||
```
|
||||
|
||||
|
|
@ -143,7 +143,7 @@ messages = context.to_openai(assistant=assistant)
|
|||
console.log(response2);
|
||||
|
||||
// Get context from the uploaded documents for LLM integration
|
||||
const context = await session.getContext({ tokens: 3000 });
|
||||
const context = await session.context({ tokens: 3000 });
|
||||
const messages = context.toOpenAI(assistant);
|
||||
})();
|
||||
```
|
||||
|
|
@ -203,7 +203,7 @@ def upload_document(file_path, description):
|
|||
|
||||
def analyze_documents():
|
||||
"""Get AI analysis of uploaded documents"""
|
||||
context = session.get_context(tokens=4000)
|
||||
context = session.context(tokens=4000)
|
||||
messages = context.to_openai(assistant=assistant)
|
||||
# Add analysis request
|
||||
messages.append({
|
||||
|
|
@ -251,7 +251,7 @@ import fs from "fs";
|
|||
}
|
||||
|
||||
async function analyzeDocuments() {
|
||||
const context = await session.getContext({ tokens: 4000 });
|
||||
const context = await session.context({ tokens: 4000 });
|
||||
const messages = context.toOpenAI(assistant);
|
||||
// Add analysis request
|
||||
messages.push({
|
||||
|
|
|
|||
|
|
@ -154,10 +154,10 @@ def chatbot(state: State):
|
|||
session.add_messages([user.message(user_message)])
|
||||
|
||||
# Step 2: Get context in OpenAI format with token limit
|
||||
# get_context() retrieves relevant conversation history
|
||||
# context() retrieves relevant conversation history
|
||||
# tokens=2000 limits the context to 2000 tokens to manage costs and fit within model limits
|
||||
# to_openai() converts it to the format expected by OpenAI's API
|
||||
messages = session.get_context(tokens=2000).to_openai(assistant=assistant)
|
||||
messages = session.context(tokens=2000).to_openai(assistant=assistant)
|
||||
|
||||
# Step 3: Generate response using the context
|
||||
response = llm.chat.completions.create(
|
||||
|
|
@ -186,10 +186,10 @@ async function chatbot(state: State) {
|
|||
await session.addMessages([user.message(userMessage)]);
|
||||
|
||||
// Step 2: Get context in OpenAI format with token limit
|
||||
// getContext() retrieves relevant conversation history
|
||||
// context() retrieves relevant conversation history
|
||||
// tokens: 2000 limits the context to 2000 tokens to manage costs and fit within model limits
|
||||
// toOpenAI() converts it to the format expected by OpenAI's API
|
||||
const messages = (await session.getContext({ tokens: 2000 })).toOpenAI(assistant);
|
||||
const messages = (await session.context({ tokens: 2000 })).toOpenAI(assistant);
|
||||
|
||||
// Step 3: Generate response using the context
|
||||
const response = await llm.chat.completions.create({
|
||||
|
|
@ -225,9 +225,9 @@ const graph = new StateGraph(StateAnnotation)
|
|||
```
|
||||
</CodeGroup>
|
||||
|
||||
### Understanding get_context()
|
||||
### Understanding context()
|
||||
|
||||
The [`get_context()`](/v3/documentation/features/get-context) method retrieves comprehensive conversation context and formats it for your LLM. It automatically:
|
||||
The [`context()`](/v3/documentation/features/get-context) method retrieves comprehensive conversation context and formats it for your LLM. It automatically:
|
||||
|
||||
- **Manages conversation history** - Tracks all messages and determines what's relevant
|
||||
- **Respects token limits** - Stays within context window constraints without manual counting
|
||||
|
|
@ -241,14 +241,14 @@ The `SessionContext` object always includes fields for messages, summaries, `pee
|
|||
- **Without `peer_perspective`**: Returns Honcho's omniscient view of `peer_target` (all conclusions and context)
|
||||
- **With `peer_perspective`**: Returns what `peer_perspective` knows about `peer_target` (perspective-based conclusions and context)
|
||||
|
||||
That's it. Call `session.get_context().to_openai(assistant)` and you get properly formatted context tailored for your assistant.
|
||||
That's it. Call `session.context().to_openai(assistant)` and you get properly formatted context tailored for your assistant.
|
||||
|
||||
<Tip>
|
||||
**Adding System Prompts:** Since `get_context()` returns conversation messages, you can easily prepend custom system instructions. Just add your system prompt to the beginning of the messages array before sending it to your LLM: `[{"role": "system", "content": "..."}, ...context_messages]`.
|
||||
**Adding System Prompts:** Since `context()` returns conversation messages, you can easily prepend custom system instructions. Just add your system prompt to the beginning of the messages array before sending it to your LLM: `[{"role": "system", "content": "..."}, ...context_messages]`.
|
||||
</Tip>
|
||||
|
||||
<Note>
|
||||
For more details on all available parameters, see [`get_context() documentation`](/v3/documentation/features/get-context)
|
||||
For more details on all available parameters, see [`context() documentation`](/v3/documentation/features/get-context)
|
||||
</Note>
|
||||
|
||||
## Chat Loop
|
||||
|
|
|
|||
|
|
@ -251,13 +251,13 @@ Reference the [API Comparison](#api-comparison) to replace your Mem0 API calls w
|
|||
| **Add messages** | `client.add(messages, user_id=...)` | `session.add_messages([peer.message(...)])` | Session-scoped, triggers reasoning |
|
||||
| **Add conclusions** | | `peer.conclusions.create([...])` | Direct conclusion or "memory" import, no processing |
|
||||
| **Search** | `client.search(query, filters={"user_id": ...})` | `peer.search(query)` or `peer.conclusions.query(...)` | Scoped to peer or session |
|
||||
| **List all** | `client.get_all(filters={"user_id": ...})` | `session.get_messages()` or `peer.conclusions.list()` | Messages or conclusions |
|
||||
| **List all** | `client.get_all(filters={"user_id": ...})` | `session.messages()` or `peer.conclusions.list()` | Messages or conclusions |
|
||||
| **Update** | `client.update(memory_id, data=...)` | `honcho.update_message(message, metadata=...)` | Metadata updates only |
|
||||
| **Delete** | `client.delete(memory_id)` | `peer.conclusions.delete(id)` or `session.delete()` | Conclusion or session-level |
|
||||
|
||||
### Honcho-Only Capabilities
|
||||
|
||||
Mem0 requires manual assembly of context from `search()` results. Honcho's `session.get_context()` returns a ready-to-use `SessionContext` object with built-in token limits, auto-included summaries, and format helpers (`.to_openai()`, `.to_anthropic()`).
|
||||
Mem0 requires manual assembly of context from `search()` results. Honcho's `session.context()` returns a ready-to-use `SessionContext` object with built-in token limits, auto-included summaries, and format helpers (`.to_openai()`, `.to_anthropic()`).
|
||||
|
||||
<Card title="Get Context" icon="window-restore" href="../../documentation/features/get-context">
|
||||
Learn more about token-optimized context retrieval
|
||||
|
|
@ -275,8 +275,8 @@ Additional features with **no Mem0 equivalent**:
|
|||
| Honcho Method | Description | Use Case |
|
||||
|---------------|-------------|----------|
|
||||
| `peer.card()` | Stable biographical facts (name, preferences, background) | User profiles, personalization |
|
||||
| `session.get_representation(peer)` | Cached psychological analysis (mental state, intentions) | Real-time adaptation |
|
||||
| `session.get_summaries()` | Auto-generated short/long session summaries | Conversation continuity |
|
||||
| `session.representation(peer)` | Cached psychological analysis (mental state, intentions) | Real-time adaptation |
|
||||
| `session.summaries()` | Auto-generated short/long session summaries | Conversation continuity |
|
||||
| `SessionPeerConfig` | Configure observation settings (who learns about whom) | Privacy controls, role-based learning |
|
||||
|
||||
## Next Steps
|
||||
|
|
|
|||
|
|
@ -146,7 +146,7 @@ def llm(session, prompt) -> str:
|
|||
|
||||
You should expand this function with custom logic, prompts, etc.
|
||||
"""
|
||||
messages: list[dict[str, object]] = session.get_context().to_openai(
|
||||
messages: list[dict[str, object]] = session.context().to_openai(
|
||||
assistant=assistant
|
||||
)
|
||||
messages.append({"role": "user", "content": prompt})
|
||||
|
|
@ -349,7 +349,7 @@ The new Honcho peer/session API makes Telegram bot integration much simpler and
|
|||
|
||||
- **Peer/Session Model**: Users are represented as peers, conversations as sessions
|
||||
- **Chat Type Handling**: Different validation logic for private vs group chats
|
||||
- **Automatic Context Management**: `session.get_context().to_openai()` automatically formats chat history
|
||||
- **Automatic Context Management**: `session.context().to_openai()` automatically formats chat history
|
||||
- **Message Storage**: `session.add_messages()` stores both user and assistant messages
|
||||
- **Dialectic Queries**: `peer.chat()` enables querying conversation history
|
||||
- **Command System**: Native Telegram command support with `/start` and `/dialectic`
|
||||
|
|
|
|||
|
|
@ -251,13 +251,13 @@ Reference the [API Comparison](#api-comparison) to replace your Mem0 API calls w
|
|||
| **Add messages** | `client.add(messages, user_id=...)` | `session.add_messages([peer.message(...)])` | Session-scoped, triggers reasoning |
|
||||
| **Add conclusions** | | `peer.conclusions.create([...])` | Direct conclusion or "memory" import, no processing |
|
||||
| **Search** | `client.search(query, filters={"user_id": ...})` | `peer.search(query)` or `peer.conclusions.query(...)` | Scoped to peer or session |
|
||||
| **List all** | `client.get_all(filters={"user_id": ...})` | `session.get_messages()` or `peer.conclusions.list()` | Messages or conclusions |
|
||||
| **List all** | `client.get_all(filters={"user_id": ...})` | `session.messages()` or `peer.conclusions.list()` | Messages or conclusions |
|
||||
| **Update** | `client.update(memory_id, data=...)` | `honcho.update_message(message, metadata=...)` | Metadata updates only |
|
||||
| **Delete** | `client.delete(memory_id)` | `peer.conclusions.delete(id)` or `session.delete()` | Conclusion or session-level |
|
||||
|
||||
### Honcho-Only Capabilities
|
||||
|
||||
Mem0 requires manual assembly of context from `search()` results. Honcho's `session.get_context()` returns a ready-to-use `SessionContext` object with built-in token limits, auto-included summaries, and format helpers (`.to_openai()`, `.to_anthropic()`).
|
||||
Mem0 requires manual assembly of context from `search()` results. Honcho's `session.context()` returns a ready-to-use `SessionContext` object with built-in token limits, auto-included summaries, and format helpers (`.to_openai()`, `.to_anthropic()`).
|
||||
|
||||
<Card title="Get Context" icon="window-restore" href="../../documentation/features/get-context">
|
||||
Learn more about token-optimized context retrieval
|
||||
|
|
@ -275,8 +275,8 @@ Additional features with **no Mem0 equivalent**:
|
|||
| Honcho Method | Description | Use Case |
|
||||
|---------------|-------------|----------|
|
||||
| `peer.card()` | Stable biographical facts (name, preferences, background) | User profiles, personalization |
|
||||
| `session.get_representation(peer)` | Cached psychological analysis (mental state, intentions) | Real-time adaptation |
|
||||
| `session.get_summaries()` | Auto-generated short/long session summaries | Conversation continuity |
|
||||
| `session.representation(peer)` | Cached psychological analysis (mental state, intentions) | Real-time adaptation |
|
||||
| `session.summaries()` | Auto-generated short/long session summaries | Conversation continuity |
|
||||
| `SessionPeerConfig` | Configure observation settings (who learns about whom) | Privacy controls, role-based learning |
|
||||
|
||||
## Next Steps
|
||||
|
|
|
|||
Loading…
Reference in New Issue