Google Vertex AI, Nanonets, LlamaIndex vs RAGFlow

The registry records Google Vertex AI as available on vendor cloud or private cloud; it is scored here as enterprise SaaS.

The registry records Nanonets as available on vendor cloud or private cloud; it is scored here as enterprise SaaS.

The registry records LlamaIndex as available on self-hosted or private cloud; it is scored here as self-hosted.

The registry records RAGFlow as available on self-hosted or private cloud; it is scored here as self-hosted.

For this brief — confidential documents — enterprise SaaS is conditional: worth it only if the conditions in the options section hold. Change the brief and this verdict changes.

For this brief — confidential documents — enterprise SaaS is conditional: worth it only if the conditions in the options section hold. Change the brief and this verdict changes.

For this brief — confidential documents — self-hosted is a strong alternative. Change the brief and this verdict changes.

For this brief — confidential documents — self-hosted is a strong alternative. Change the brief and this verdict changes.

Covers your main objective (data extraction) and 2 of 2 secondary objectives (document Q&A, internal company search).

Covers your main objective (data extraction) and 0 of 2 secondary objectives.

Covers your main objective (data extraction) and 2 of 2 secondary objectives (document Q&A, internal company search).

Covers your main objective (data extraction) and 2 of 2 secondary objectives (document Q&A, internal company search).

You stated no hosting preference, so no option is favoured on that basis. No hard restriction on where processing happens was stated. Headcount was not stated, so the size band could not be checked.

You stated no hosting preference, so no option is favoured on that basis. No hard restriction on where processing happens was stated. Headcount was not stated, so the size band could not be checked.

You stated no hosting preference, so no option is favoured on that basis. No hard restriction on where processing happens was stated. Headcount was not stated, so the size band could not be checked.

You stated no hosting preference, so no option is favoured on that basis. No hard restriction on where processing happens was stated. Headcount was not stated, so the size band could not be checked.

External data transfer: yes. No catalogue deployment names Google Vertex AI, so this is read from “Enterprise SaaS assistant with governance controls”, the best-matching enterprise SaaS deployment for this brief. Confidential content leaves your control on the Employees → Vendor assistant (web and desktop clients) link.

External data transfer: yes. No catalogue deployment names Nanonets, so this is read from “Enterprise SaaS assistant with governance controls”, the best-matching enterprise SaaS deployment for this brief. Confidential content leaves your control on the Employees → Vendor assistant (web and desktop clients) link.

External data transfer: none. No catalogue deployment names LlamaIndex, so this is read from “Contract review and clause extraction”, the best-matching self-hosted deployment for this brief. No edge in this design crosses out of the company network.

External data transfer: none. Computed from “Private company knowledge base (self-hosted RAG)”, the catalogue deployment that names RAGFlow and best matches this brief. No edge in this design crosses out of the company network.

We hold no fetched residency commitment for Google Vertex AI. That is a question to put to the vendor, not an assumption to make about them. The vendor is headquartered in the United States, which is where a transfer question starts, not where it ends.

We hold no fetched residency commitment for Nanonets. That is a question to put to the vendor, not an assumption to make about them.

Self-hosted: the content stays wherever you run the server, so residency is a property of your own infrastructure rather than a vendor commitment.

Self-hosted: the content stays wherever you run the server, so residency is a property of your own infrastructure rather than a vendor commitment.

We have fetched none of the four commitments for Google Vertex AI: data processing agreement, subprocessor list, training on customer data, zero retention option. Each is a question for the vendor, and until it is answered it is unknown rather than absent.

We have fetched none of the four commitments for Nanonets: data processing agreement, subprocessor list, training on customer data, zero retention option. Each is a question for the vendor, and until it is answered it is unknown rather than absent.

Run on your own infrastructure, so the vendor questions apply only to whatever you still buy. We hold none of the four commitments for this subject, and for a self-hosted deployment none of them is required.

Run on your own infrastructure, so the vendor questions apply only to whatever you still buy. We hold none of the four commitments for this subject, and for a self-hosted deployment none of them is required.

4–12 FDE-days to implement. No catalogue deployment names Google Vertex AI, so this is read from “Enterprise SaaS assistant with governance controls”, the best-matching enterprise SaaS deployment for this brief.

4–12 FDE-days to implement. No catalogue deployment names Nanonets, so this is read from “Enterprise SaaS assistant with governance controls”, the best-matching enterprise SaaS deployment for this brief.

10–25 FDE-days to implement. No catalogue deployment names LlamaIndex, so this is read from “Contract review and clause extraction”, the best-matching self-hosted deployment for this brief.

8–20 FDE-days to implement. Computed from “Private company knowledge base (self-hosted RAG)”, the catalogue deployment that names RAGFlow and best matches this brief.

The vendor runs the service. Your standing work is access control, the policy staff work under, and re-reading the contract and subprocessor list when they change — not patching or capacity.

The vendor runs the service. Your standing work is access control, the policy staff work under, and re-reading the contract and subprocessor list when they change — not patching or capacity.

You own GPU drivers and the model server, the connectors and their credentials, operating-system patching and backups. Assessed difficulty 3/5 is the shape of that work; someone has to hold it after go-live.

You own GPU drivers and the model server, the identity integration and joiner/leaver process, operating-system patching and backups. Assessed difficulty 3/5 is the shape of that work; someone has to hold it after go-live.

2/5. Starting point 1/5: a vendor product, configured rather than installed. +0.5 Single sign-on adds an identity provider, group-to-role mapping and a joiner/leaver process to the deployment.

2/5. Starting point 1/5: a vendor product, configured rather than installed. +0.5 Single sign-on adds an identity provider, group-to-role mapping and a joiner/leaver process to the deployment.

3/5. Starting point 2/5: software you install, run and keep running on your own machines. +0.5 You run the model server yourself: GPU drivers, quantisation choice, memory headroom and restarts are all yours to own.

3/5. Starting point 2/5: software you install, run and keep running on your own machines. +0.5 You run the model server yourself: GPU drivers, quantisation choice, memory headroom and restarts are all yours to own.

USD 3,100 – 23,000 — one-off — for Google Vertex AI at this headcount. No catalogue deployment names Google Vertex AI, so this is read from “Enterprise SaaS assistant with governance controls”, the best-matching enterprise SaaS deployment for this brief. Licences are not in that figure: no per-seat price has been read from the vendor’s own pricing page, so the software line is excluded from the total rather than guessed. Read it as implementation only.

USD 3,100 – 23,000 — one-off — for Nanonets at this headcount. No catalogue deployment names Nanonets, so this is read from “Enterprise SaaS assistant with governance controls”, the best-matching enterprise SaaS deployment for this brief. Licences are not in that figure: no per-seat price has been read from the vendor’s own pricing page, so the software line is excluded from the total rather than guessed. Read it as implementation only.

USD 20,000 – 70,000 — one-off — for LlamaIndex at this headcount. No catalogue deployment names LlamaIndex, so this is read from “Contract review and clause extraction”, the best-matching self-hosted deployment for this brief.

USD 10,000 – 48,000 — one-off — for RAGFlow at this headcount. Computed from “Private company knowledge base (self-hosted RAG)”, the catalogue deployment that names RAGFlow and best matches this brief.

Google Vertex AI is a vendor product: you configure what the vendor exposes — policies, connectors, retention settings — and nothing below that line.

Nanonets is a vendor product: you configure what the vendor exposes — policies, connectors, retention settings — and nothing below that line.

The registry files LlamaIndex as open source, so the interface, retrieval behaviour and the model behind it can be changed — subject to the licence, which is a fetched fact on its own page.

The registry files RAGFlow as open source, so the interface, retrieval behaviour and the model behind it can be changed — subject to the licence, which is a fetched fact on its own page.

8 issues spotted for this brief, 0 of them legal requirements; 0 carry a quote from the instrument they rest on. Leading with: Confidentiality duties bind independently of data protection law.

8 issues spotted for this brief, 0 of them legal requirements; 0 carry a quote from the instrument they rest on. Leading with: Confidentiality duties bind independently of data protection law.

7 issues spotted for this brief, 0 of them legal requirements; 0 carry a quote from the instrument they rest on. Leading with: Self-hosting moves the security obligation to you.

7 issues spotted for this brief, 0 of them legal requirements; 0 carry a quote from the instrument they rest on. Leading with: Self-hosting moves the security obligation to you.