From 75e2679cf1dc8a94ee367320bea138c371e044fe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicol=C3=B2=20Boschi?= Date: Mon, 30 Mar 2026 18:34:25 +0200 Subject: [PATCH] release(llamaindex): v0.1.3 --- .../src/pages/changelog/integrations/llamaindex.md | 6 ++++++ hindsight-integrations/llamaindex/pyproject.toml | 2 +- .../references/changelog/integrations/llamaindex.md | 6 ++++++ .../references/developer/configuration.md | 2 ++ .../references/sdks/integrations/llamaindex.md | 13 ++++++++----- 5 files changed, 23 insertions(+), 6 deletions(-) diff --git a/hindsight-docs/src/pages/changelog/integrations/llamaindex.md b/hindsight-docs/src/pages/changelog/integrations/llamaindex.md index 160be696..90aae945 100644 --- a/hindsight-docs/src/pages/changelog/integrations/llamaindex.md +++ b/hindsight-docs/src/pages/changelog/integrations/llamaindex.md @@ -10,6 +10,12 @@ For the source code, see [`hindsight-integrations/llamaindex`](https://github.co ← [Back to main changelog](/changelog) +## [0.1.3](https://github.com/vectorize-io/hindsight/tree/integrations/llamaindex/v0.1.3) + +**Bug Fixes** + +- Fixed LlamaIndex integration issues with document IDs, the memory API, and ReAct trace handling to improve reliability and correctness. ([`d93dfea8`](https://github.com/vectorize-io/hindsight/commit/d93dfea8)) + ## [0.1.2](https://github.com/vectorize-io/hindsight/tree/integrations/llamaindex/v0.1.2) **Features** diff --git a/hindsight-integrations/llamaindex/pyproject.toml b/hindsight-integrations/llamaindex/pyproject.toml index 9800ef2b..9fb0f811 100644 --- a/hindsight-integrations/llamaindex/pyproject.toml +++ b/hindsight-integrations/llamaindex/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "hindsight-llamaindex" -version = "0.1.2" +version = "0.1.3" description = "LlamaIndex integration for Hindsight - persistent memory for AI agents" readme = "README.md" requires-python = ">=3.10" diff --git a/skills/hindsight-docs/references/changelog/integrations/llamaindex.md b/skills/hindsight-docs/references/changelog/integrations/llamaindex.md index a1ac433f..ddf4b607 100644 --- a/skills/hindsight-docs/references/changelog/integrations/llamaindex.md +++ b/skills/hindsight-docs/references/changelog/integrations/llamaindex.md @@ -10,6 +10,12 @@ For the source code, see [`hindsight-integrations/llamaindex`](https://github.co ← [Back to main changelog](../index.md) +## [0.1.3](https://github.com/vectorize-io/hindsight/tree/integrations/llamaindex/v0.1.3) + +**Bug Fixes** + +- Fixed LlamaIndex integration issues with document IDs, the memory API, and ReAct trace handling to improve reliability and correctness. ([`d93dfea8`](https://github.com/vectorize-io/hindsight/commit/d93dfea8)) + ## [0.1.2](https://github.com/vectorize-io/hindsight/tree/integrations/llamaindex/v0.1.2) **Features** diff --git a/skills/hindsight-docs/references/developer/configuration.md b/skills/hindsight-docs/references/developer/configuration.md index ee5f6f14..7aa586fb 100644 --- a/skills/hindsight-docs/references/developer/configuration.md +++ b/skills/hindsight-docs/references/developer/configuration.md @@ -464,6 +464,7 @@ Supported OpenAI embedding dimensions: | `HINDSIGHT_API_RERANKER_LITELLM_MAX_TOKENS_PER_DOC` | Truncate documents to this many tokens before sending to the reranker (applies to both `litellm` and `litellm-sdk`). Use for models with small context windows (e.g. set to `900` for a 1024-token limit model). Unset by default (no truncation). | - | | `HINDSIGHT_API_RERANKER_ZEROENTROPY_API_KEY` | ZeroEntropy API key for reranking | - | | `HINDSIGHT_API_RERANKER_ZEROENTROPY_MODEL` | ZeroEntropy rerank model (`zerank-2`, `zerank-2-small`) | `zerank-2` | +| `HINDSIGHT_API_RERANKER_ZEROENTROPY_BASE_URL` | Custom base URL for ZeroEntropy-compatible API (e.g., mock server, proxy, or self-hosted deployment) | `https://api.zeroentropy.dev` | | `HINDSIGHT_API_RERANKER_FLASHRANK_MODEL` | FlashRank model for fast CPU-based reranking | `ms-marco-MiniLM-L-12-v2` | | `HINDSIGHT_API_RERANKER_FLASHRANK_CACHE_DIR` | Cache directory for FlashRank models | System default | | `HINDSIGHT_API_RERANKER_JINA_MLX_MODEL_PATH` | Local path to downloaded `jina-reranker-v3-mlx` model (auto-downloads from HuggingFace if unset) | - | @@ -498,6 +499,7 @@ export HINDSIGHT_API_RERANKER_COHERE_BASE_URL=https://your-azure-cohere-endpoint export HINDSIGHT_API_RERANKER_PROVIDER=zeroentropy export HINDSIGHT_API_RERANKER_ZEROENTROPY_API_KEY=your-api-key export HINDSIGHT_API_RERANKER_ZEROENTROPY_MODEL=zerank-2 # or zerank-2-small +# export HINDSIGHT_API_RERANKER_ZEROENTROPY_BASE_URL=https://your-custom-endpoint.com # optional # LiteLLM proxy - unified gateway for multiple reranking providers (requires running LiteLLM proxy server) export HINDSIGHT_API_RERANKER_PROVIDER=litellm diff --git a/skills/hindsight-docs/references/sdks/integrations/llamaindex.md b/skills/hindsight-docs/references/sdks/integrations/llamaindex.md index 0f95feb3..0310b98f 100644 --- a/skills/hindsight-docs/references/sdks/integrations/llamaindex.md +++ b/skills/hindsight-docs/references/sdks/integrations/llamaindex.md @@ -37,8 +37,8 @@ async def main(): mission="Track user preferences and project context", ) - agent = ReActAgent(tools=[], llm=OpenAI(model="gpt-4o"), memory=memory) - response = await agent.run("Remember that I prefer dark mode") + agent = ReActAgent(tools=[], llm=OpenAI(model="gpt-4o")) + response = await agent.run("Remember that I prefer dark mode", memory=memory) print(response) asyncio.run(main()) @@ -48,8 +48,8 @@ asyncio.run(main()) | Event | What Happens | |-------|-------------| -| Agent receives input | `get(input)` recalls relevant memories from Hindsight, prepends as system message | -| Agent produces output | `put(message)` retains the message to Hindsight for future recall | +| Agent receives input | `aget(input)` recalls relevant memories from Hindsight, prepends as system message | +| Agent produces output | `aput(message)` retains the message to Hindsight for future recall | | New session starts | Previous memories are available via recall; local chat buffer starts empty | ### `HindsightMemory.from_client()` @@ -236,7 +236,10 @@ tools = create_hindsight_tools( include_reflect=True, # agent can still explicitly reflect ) -agent = ReActAgent(tools=tools, llm=llm, memory=memory) +agent = ReActAgent(tools=tools, llm=llm) + +# Pass memory to run() +response = await agent.run("What should I prioritize?", memory=memory) ``` ## Requirements