add run benchmarks instructions

hindsight-dev/benchmarks/README.md

@@ -0,0 +1,82 @@
+# Hindsight Benchmarks
+
+This directory contains benchmark suites for evaluating Hindsight's memory capabilities.
+
+## Prerequisites
+
+1. Set up your environment variables in `.env` at the project root:
+   ```bash
+   cp .env.example .env
+   # Edit .env with your API keys
+   ```
+
+2. Make sure you have `uv` installed.
+
+## Available Benchmarks
+
+### LoComo
+
+Tests conversational memory with multi-turn dialogues.
+
+```bash
+# Run from project root
+./scripts/benchmarks/run-locomo.sh
+
+# With options
+./scripts/benchmarks/run-locomo.sh --max-conversations 10
+./scripts/benchmarks/run-locomo.sh --skip-ingestion  # Reuse existing data
+./scripts/benchmarks/run-locomo.sh --use-think       # Use think API
+./scripts/benchmarks/run-locomo.sh --conversation conv-26  # Single conversation
+```
+
+**Options:**
+- `--max-conversations N` - Limit number of conversations
+- `--max-questions N` - Limit questions per conversation
+- `--skip-ingestion` - Skip data ingestion, use existing
+- `--use-think` - Use think API instead of search + LLM
+- `--conversation NAME` - Run specific conversation only
+- `--api-url URL` - Custom API URL (default: local memory)
+- `--only-failed` - Retry only failed questions
+- `--only-invalid` - Retry only invalid questions
+
+### LongMemEval
+
+Tests long-term memory across different categories.
+
+```bash
+# Run from project root
+./scripts/benchmarks/run-longmemeval.sh
+
+# With options
+./scripts/benchmarks/run-longmemeval.sh --max-instances 50
+./scripts/benchmarks/run-longmemeval.sh --category single-session-user
+./scripts/benchmarks/run-longmemeval.sh --parallel 4  # Faster evaluation
+```
+
+**Options:**
+- `--max-instances N` - Limit total questions
+- `--max-instances-per-category N` - Limit per category
+- `--skip-ingestion` - Skip data ingestion
+- `--category NAME` - Filter by category:
+  - `single-session-user`
+  - `multi-session`
+  - `single-session-preference`
+  - `temporal-reasoning`
+  - `knowledge-update`
+  - `single-session-assistant`
+- `--parallel N` - Parallel instances (default: 1)
+- `--only-failed` - Retry failed questions
+- `--fill` - Resume interrupted runs
+
+## Visualizer
+
+View benchmark results in a web UI:
+
+```bash
+./scripts/benchmarks/start-visualizer.sh
+# Opens at http://localhost:8001
+```
+
+## Results
+
+Results are saved in JSON format in each benchmark's `results/` directory.

uv.lock

@@ -1141,7 +1141,7 @@ wheels = [
 
 [[package]]
 name = "hindsight-all"
-version = "0.1.6"
+version = "0.1.7"
 source = { editable = "hindsight" }
 dependencies = [
     { name = "hindsight-api" },
@@ -1165,7 +1165,7 @@ provides-extras = ["test"]
 
 [[package]]
 name = "hindsight-api"
-version = "0.1.6"
+version = "0.1.7"
 source = { editable = "hindsight-api" }
 dependencies = [
     { name = "alembic" },
@@ -1249,7 +1249,7 @@ requires-dist = [
     { name = "sentence-transformers", specifier = ">=3.0.0,<3.3.0" },
     { name = "sqlalchemy", specifier = ">=2.0.44" },
     { name = "tiktoken", specifier = ">=0.12.0" },
-    { name = "torch", specifier = ">=2.0.0,<2.6.0" },
+    { name = "torch", specifier = ">=2.0.0" },
     { name = "transformers", specifier = ">=4.30.0,<4.46.0" },
     { name = "uvicorn", specifier = ">=0.38.0" },
     { name = "wsproto", specifier = ">=1.0.0" },
@@ -1269,7 +1269,7 @@ dev = [
 
 [[package]]
 name = "hindsight-client"
-version = "0.1.6"
+version = "0.1.7"
 source = { editable = "hindsight-clients/python" }
 dependencies = [
     { name = "aiohttp" },
@@ -1301,7 +1301,7 @@ provides-extras = ["test"]
 
 [[package]]
 name = "hindsight-dev"
-version = "0.1.6"
+version = "0.1.7"
 source = { editable = "hindsight-dev" }
 dependencies = [
     { name = "hindsight-api" },